Compare commits
1 Commits
e587e58cb2
...
031a70e0b6
| Author | SHA1 | Date | |
|---|---|---|---|
| 031a70e0b6 |
9
LICENSE
9
LICENSE
@@ -682,7 +682,14 @@ under their own licenses. They are NOT covered by the GPL-3.0 license above.
|
||||
|
||||
---------------------------------------------------------------------------
|
||||
File: src/shared/phishingBlocklist.json
|
||||
Source: https://github.com/AugurProject/eth-phishing-detect (config.json)
|
||||
Source: the eth-phishing-detect community blocklist (src/config.json).
|
||||
The file here is derived from it, not a copy of it: only the
|
||||
blacklist is carried over, and each entry is stored as a truncated
|
||||
digest rather than a domain name. script/vendor-blocklist records
|
||||
the exact upstream URL, the commit it is pinned to and the hash of
|
||||
the bytes that commit serves, and is what regenerates this file.
|
||||
The URL previously cited here, under a different organisation,
|
||||
returns 404: that repository is gone.
|
||||
Copyright: Copyright (c) 2018 kumavis
|
||||
License: Don't Be a Dick Public License (DBAD), Version 1.2
|
||||
---------------------------------------------------------------------------
|
||||
|
||||
16
Makefile
16
Makefile
@@ -1,4 +1,4 @@
|
||||
.PHONY: bootstrap setup install test test-e2e test-e2e-firefox lint fmt fmt-check check docker hooks build build-debug verify-build clean dev
|
||||
.PHONY: bootstrap setup install test test-e2e test-e2e-firefox lint fmt fmt-check check check-censored docker hooks build build-debug verify-build vendor-blocklist clean dev
|
||||
|
||||
# Standard targets are thin shims; the implementations live in script/
|
||||
# per the scripts-to-rule-them-all pattern (see the Entrypoints section
|
||||
@@ -35,6 +35,12 @@ fmt-check:
|
||||
check:
|
||||
@script/check
|
||||
|
||||
# Assert that the competitor name appears nowhere but its documented
|
||||
# exceptions. Part of check, and re-run against dist/ at the end of a build;
|
||||
# separate target for re-running it alone.
|
||||
check-censored:
|
||||
@script/check-censored
|
||||
|
||||
docker:
|
||||
@script/docker
|
||||
|
||||
@@ -45,6 +51,7 @@ build:
|
||||
@echo "Building extension..."
|
||||
@yarn run build 2>&1
|
||||
@script/verify-build
|
||||
@script/check-censored --require-dist
|
||||
|
||||
# Development-only build: enables the red DEBUG / INSECURE banner and makes
|
||||
# the hardcoded test recovery phrase the output of wallet creation. Never
|
||||
@@ -53,12 +60,19 @@ build-debug:
|
||||
@echo "Building extension (DEBUG)..."
|
||||
@AUTISTMASK_DEBUG=1 yarn run build 2>&1
|
||||
@AUTISTMASK_DEBUG=1 script/verify-build
|
||||
@script/check-censored --require-dist
|
||||
|
||||
# Assert the compiled DEBUG state of the bundles already in dist/. Runs at
|
||||
# the end of build and build-debug; separate target for re-running it alone.
|
||||
verify-build:
|
||||
@script/verify-build
|
||||
|
||||
# Refresh src/shared/phishingBlocklist.json from its hash-pinned upstream.
|
||||
# Run deliberately, land the diff: the extension does no runtime fetching, so
|
||||
# the shipped list is as fresh as the last vendoring run that was released.
|
||||
vendor-blocklist:
|
||||
@script/vendor-blocklist
|
||||
|
||||
clean:
|
||||
@rm -rf dist/
|
||||
|
||||
|
||||
178
README.md
178
README.md
@@ -18,9 +18,10 @@ don't implement any crypto, and don't send user-specific data anywhere but a
|
||||
extension contacts three user-configurable services: the configured RPC node for
|
||||
blockchain interactions, a public CoinDesk API (no API key) for realtime price
|
||||
information, and a Blockscout block-explorer API for transaction history and
|
||||
token balances. It also fetches a community-maintained phishing domain blocklist
|
||||
periodically and performs best-effort Etherscan address label lookups during
|
||||
transaction confirmation.
|
||||
token balances. It also performs best-effort Etherscan address label lookups
|
||||
during transaction confirmation. A community-maintained phishing domain
|
||||
blocklist is built into the extension at build time and checked locally; nothing
|
||||
is fetched for it at runtime.
|
||||
|
||||
In the extension is a hardcoded list of the top ERC20 contract addresses. You
|
||||
can add any ERC20 contract by contract address if you wish, but the hardcoded
|
||||
@@ -98,7 +99,21 @@ provide:
|
||||
the same script lint in place instead of recursing.
|
||||
- `script/fmt` — format all files (writes)
|
||||
- `script/fmt-check` — check formatting (read-only)
|
||||
- `script/check` — run test, test-verify-build, lint, and fmt-check
|
||||
- `script/check` — run test, test-verify-build, check-censored, lint, and
|
||||
fmt-check
|
||||
- `script/check-censored` — assert the competitor name RULES.md bars appears
|
||||
nowhere in the working tree or under `dist/` outside its documented
|
||||
exceptions: the pinned source reference in `script/vendor-blocklist`, the two
|
||||
provider-shim identifiers in `src/content/inpage.js`, and one ERC-20's
|
||||
on-chain name in `src/shared/tokenList.js`. Each is scoped to that path and
|
||||
fails anywhere else. Part of `make check`, which inspects `dist/` when there
|
||||
is one and says loudly when there is not; `make build` re-runs it with
|
||||
`--require-dist`, so a build artifact is always covered
|
||||
- `script/vendor-blocklist` — refresh `src/shared/phishingBlocklist.json` from
|
||||
its upstream, pinned to a commit and to the sha256 of the bytes that commit
|
||||
serves. Run deliberately, never as part of a build: the output is committed
|
||||
and there is no runtime fetch, so the shipped list is as fresh as the last
|
||||
vendoring run that was released
|
||||
- `script/verify-build` — assert the compiled `DEBUG` state of the bundles in
|
||||
`dist/`: every bundle containing `src/shared/constants.js` must have `DEBUG`
|
||||
off, or on when `AUTISTMASK_DEBUG=1`. Run automatically at the end of
|
||||
@@ -238,16 +253,16 @@ That interception covers the MV3 background service worker as well as the popup
|
||||
page, which it does not by default — `script/test-e2e` sets
|
||||
`PW_EXPERIMENTAL_SERVICE_WORKER_NETWORK_EVENTS=1` for it. Because that flag is
|
||||
experimental, the harness does not take it on trust. At launch it waits for the
|
||||
background worker's **own** startup request — the phishing blocklist fetch that
|
||||
`src/background/index.js` issues on startup, which on the suite's throwaway
|
||||
profile always happens because no previous fetch timestamp is persisted — to
|
||||
arrive in the route handler, and aborts the entire suite if none does within 30
|
||||
seconds (`tests/e2e/harness.js`). The check is passive on purpose: a synthetic
|
||||
probe fetched from inside the worker via `worker.evaluate()` was tried first and
|
||||
rejected, because evaluating in an extension service worker that early kills the
|
||||
worker outright, destroying the thing being measured. Observing traffic the
|
||||
extension already generates perturbs nothing. Losing the race fails closed — the
|
||||
suite refuses to run rather than passing quietly.
|
||||
background worker to exist, asks it for one throwaway `fetch()` of its own, and
|
||||
requires that request to arrive in the route handler within 30 seconds or aborts
|
||||
the entire suite (`tests/e2e/harness.js`). The anchor used to be the worker's
|
||||
own startup traffic — the phishing blocklist fetch — and there is no longer any:
|
||||
the blocklist is vendored at build time and the extension contacts nobody when
|
||||
it starts. An earlier synthetic probe was rejected because evaluating in an
|
||||
extension service worker immediately after launch killed the worker outright;
|
||||
waiting for the worker to be handed over first, and issuing a `fetch()` that is
|
||||
not awaited, does not. Failing the probe fails closed — the suite refuses to run
|
||||
rather than passing quietly.
|
||||
|
||||
As defence in depth, Chrome is also started with
|
||||
`--host-resolver-rules=MAP * ~NOTFOUND`, so a request that ever did slip past
|
||||
@@ -496,60 +511,46 @@ on the next event. Two consequences shape every recurring job in the background:
|
||||
|
||||
- `setInterval` and `setTimeout` are useless. They are destroyed with the
|
||||
worker, so a job scheduled that way runs until the first idle period and never
|
||||
again. Both recurring jobs — the 60-second balance refresh and the 24-hour
|
||||
phishing blocklist refresh — are scheduled through the extension alarms API
|
||||
(`src/shared/alarms.js`) instead. The browser holds the schedule and wakes the
|
||||
worker to deliver it. Alarm periods are clamped to a one-minute minimum, so
|
||||
the balance refresh is expressed as exactly one minute and nothing is silently
|
||||
slowed down.
|
||||
again. The one recurring job — the 60-second balance refresh — is scheduled
|
||||
through the extension alarms API (`src/shared/alarms.js`) instead. The browser
|
||||
holds the schedule and wakes the worker to deliver it. Alarm periods are
|
||||
clamped to a one-minute minimum, so the balance refresh is expressed as
|
||||
exactly one minute and nothing is silently slowed down.
|
||||
- Module-level variables do not survive either. Anything that must be remembered
|
||||
across a restart goes in extension storage, including the timestamp of the
|
||||
last phishing list fetch: without it a revived worker would either re-fetch on
|
||||
every wake or, with a naive in-memory guard, never notice that an update is
|
||||
due. `localStorage` does not exist in a service worker at all — the one
|
||||
remaining user of it, `src/shared/ens.js`, runs only in the popup and is
|
||||
marked as such.
|
||||
across a restart goes in extension storage. `localStorage` does not exist in a
|
||||
service worker at all — the one remaining user of it, `src/shared/ens.js`,
|
||||
runs only in the popup and is marked as such.
|
||||
|
||||
Both jobs also carry a freshness guard, and a guard must never be timed to the
|
||||
alarm period it gates. Each guard is measured from the moment the last run
|
||||
The job also carries a freshness guard, and a guard must never be timed to the
|
||||
alarm period it gates. The guard is measured from the moment the last run
|
||||
finished, which is one run-duration after the alarm that started it, so a guard
|
||||
of exactly one period vetoes the very next tick and the real cadence becomes two
|
||||
periods. The two jobs solve this differently, because their guards exist for
|
||||
different reasons:
|
||||
periods. The balance refresh guard exists to skip work an open popup has already
|
||||
done — the popup refreshes every 10 seconds and stamps the same field — and that
|
||||
has to keep applying on the scheduled tick, so the guard is shortened to half
|
||||
the alarm period rather than bypassed: comfortably above the popup's 10 seconds,
|
||||
so an open popup still suppresses the background job, and comfortably below the
|
||||
60-second period, so the schedule always wins.
|
||||
|
||||
- The phishing refresh has a 24-hour cache TTL whose job is to keep the worker
|
||||
off the network on the wakes between scheduled refreshes — Chrome revives the
|
||||
worker every ~30 seconds while the browser is busy, and every revival runs the
|
||||
startup path. The scheduled alarm tick is not one of those wakes, so it
|
||||
bypasses the TTL and fetches unconditionally. Shortening the TTL instead would
|
||||
not work: the startup path re-checks it on every wake, so a shorter TTL simply
|
||||
becomes the real refresh rate.
|
||||
- The balance refresh guard exists to skip work an open popup has already done —
|
||||
the popup refreshes every 10 seconds and stamps the same field. That has to
|
||||
keep applying on the scheduled tick, so the guard is shortened to half the
|
||||
alarm period instead of bypassed: comfortably above the popup's 10 seconds, so
|
||||
an open popup still suppresses the background job, and comfortably below the
|
||||
60-second period, so the schedule always wins.
|
||||
Retiring a job means clearing its alarm, not just deleting its handler. The
|
||||
browser keeps an alarm until something removes it, so an install that once ran
|
||||
the version which created it goes on being woken on that schedule forever. Names
|
||||
that are no longer handled are listed in `OBSOLETE_ALARMS` and cleared on every
|
||||
start; the 24-hour phishing blocklist refresh is there, retired when the runtime
|
||||
fetch was removed.
|
||||
|
||||
Two timestamps are persisted for the phishing list, not one. `lastFetchTime`
|
||||
records a fetch that produced a usable delta and drives the TTL.
|
||||
`lastAttemptTime` records that the network was contacted at all, and is written
|
||||
even when the result is unusable — a failed request, or a delta over the 256 KiB
|
||||
cap. Without it those cases leave no freshness mark and the worker re-downloads
|
||||
the full blocklist on every wake, indefinitely; with it, unscheduled retries are
|
||||
floored at one hour. Both are discarded on load if they are in the future, since
|
||||
a stamp from a skewed clock or a restored backup would otherwise suppress
|
||||
updates until that time arrives, permanently and with no way out.
|
||||
The startup path (`ensureRecurringAlarms()`) runs on `onInstalled`, on
|
||||
`onStartup`, and at the top level of the worker, so every way the background
|
||||
context can start re-establishes the schedule. On a fresh install more than one
|
||||
of those fires, so they share a single in-flight run rather than racing. It is
|
||||
idempotent: an alarm that already exists with the period the code asks for is
|
||||
left alone, because re-creating one restarts its schedule and a busy extension
|
||||
would push the next fire out indefinitely. An alarm carrying a different period
|
||||
— one created by an earlier version — is re-created once, or a period changed in
|
||||
a new release would never reach an existing install.
|
||||
|
||||
The startup path (`ensureRecurringAlarms()` plus the phishing list init) runs on
|
||||
`onInstalled`, on `onStartup`, and at the top level of the worker, so every way
|
||||
the background context can start re-establishes the schedule. On a fresh install
|
||||
more than one of those fires, so they share a single in-flight run rather than
|
||||
racing. It is idempotent: an alarm that already exists with the period the code
|
||||
asks for is left alone, because re-creating one restarts its schedule and a busy
|
||||
extension would push the next fire out indefinitely. An alarm carrying a
|
||||
different period — one created by an earlier version — is re-created once, or a
|
||||
period changed in a new release would never reach an existing install.
|
||||
Nothing is fetched when the worker starts. A wake costs no network traffic at
|
||||
all, which is what the phishing blocklist being vendored at build time bought.
|
||||
|
||||
Firefox uses Manifest V2 with a persistent background page, where timers would
|
||||
survive. Both browsers are built from one bundle and both take the alarm path,
|
||||
@@ -1412,17 +1413,6 @@ What the extension does NOT do:
|
||||
In addition to the three user-configurable services above (RPC endpoint,
|
||||
CoinDesk price API, and Blockscout API), AutistMask also contacts:
|
||||
|
||||
- **Phishing domain blocklist**: A community-maintained phishing domain
|
||||
blocklist is vendored into the extension at build time. At runtime, the
|
||||
extension fetches the live list once every 24 hours to detect newly added
|
||||
domains, plus once on a start where the list is more than 24 hours old. Only
|
||||
the delta (domains not already in the vendored list) is kept in memory,
|
||||
keeping runtime memory usage small. The delta and the timestamp of the fetch
|
||||
that produced it are persisted to extension storage if the record is under 256
|
||||
KiB; an oversized delta is dropped along with its timestamp, so a later start
|
||||
fetches again rather than claiming freshness for data it no longer holds. A
|
||||
fetch that fails, or one whose delta was too large to store, is not retried
|
||||
more than once an hour outside the 24-hour schedule.
|
||||
- **Etherscan address labels**: When confirming a transaction, the extension
|
||||
performs a best-effort lookup of the recipient address on Etherscan to check
|
||||
for phishing/scam labels. This is a direct page fetch with no API key; the
|
||||
@@ -1693,17 +1683,25 @@ indexes it as a real token transfer.
|
||||
|
||||
AutistMask protects users from known phishing sites when they connect their
|
||||
wallet or approve transactions/signatures. A community-maintained domain
|
||||
blocklist is vendored into the extension at build time, providing immediate
|
||||
protection without any network requests. At runtime, the extension fetches the
|
||||
live list once every 24 hours and keeps only the delta (newly added domains not
|
||||
in the vendored list) in memory. This architecture keeps runtime memory usage
|
||||
small while ensuring fresh coverage of new phishing domains.
|
||||
blocklist is vendored into the extension at build time and checked entirely
|
||||
locally: no network request is made for it, ever, so nobody learns which sites
|
||||
the user connects to and no third party decides what this wallet warns about.
|
||||
|
||||
The 24-hour cadence is an alarm, not a timer; the alarm tick fetches
|
||||
unconditionally rather than re-checking the 24-hour cache TTL that gates the
|
||||
startup path; and the fetch timestamps live in extension storage rather than in
|
||||
module variables — see [Background scheduling](#background-scheduling) for why
|
||||
all three are required.
|
||||
The trade is freshness. The shipped list is exactly as current as the last
|
||||
vendoring run that was released, so a domain added upstream reaches users in the
|
||||
next release rather than within a day. Refreshing it is `make vendor-blocklist`,
|
||||
which fetches a hash-pinned upstream commit, verifies the sha256 of the bytes it
|
||||
was served, and rewrites `src/shared/phishingBlocklist.json`; the diff is
|
||||
committed and ships with the next version.
|
||||
|
||||
The artifact holds digests, not domain names: sha256 truncated to 64 bits, one
|
||||
entry per 16 hex characters, concatenated in sorted order into a single string
|
||||
(`src/shared/domainHash.js`). A lookup hashes the hostname and its parent
|
||||
domains and binary-searches that string, so nothing is built at module load —
|
||||
which matters on MV3, where the worker re-evaluates the module on every wake —
|
||||
and the file is 1.7 MB rather than 8.7 MB. Storing digests is also what makes a
|
||||
list assembled elsewhere shippable here at all: the extension carries no
|
||||
plaintext list of anyone's domain names.
|
||||
|
||||
When a dApp on a blocklisted domain requests a wallet connection, transaction
|
||||
approval, or signature, the approval popup displays a prominent red warning
|
||||
@@ -1800,17 +1798,23 @@ covered by the GPL-3.0 license above. These files, their copyright holders, and
|
||||
their licenses are:
|
||||
|
||||
| File | Source | Copyright | License |
|
||||
| ---------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- | --------------------------------- | -------------------------------------------------------------- |
|
||||
| `src/shared/phishingBlocklist.json` | `eth-phishing-detect` community-maintained phishing domain blocklist, vendored from its `src/config.json` | Copyright (c) 2018 kumavis | [DBAD (Don't Be a Dick)](https://github.com/philsturgeon/dbad) |
|
||||
| ---------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | --------------------------------- | -------------------------------------------------------------- |
|
||||
| `src/shared/phishingBlocklist.json` | `eth-phishing-detect` community-maintained phishing domain blocklist, derived from its `src/config.json` | Copyright (c) 2018 kumavis | [DBAD (Don't Be a Dick)](https://github.com/philsturgeon/dbad) |
|
||||
| `src/shared/scamlist.js` (address data from MyEtherWallet) | [ethereum-lists](https://github.com/MyEtherWallet/ethereum-lists) `addresses-darklist.json` | Copyright (c) 2020 MyEtherWallet | MIT |
|
||||
| `src/shared/scamlist.js` (address data from EtherScamDB) | [EtherScamDB](https://github.com/MrLuit/EtherScamDB) `scams.yaml` | Copyright (c) 2018 Luit Hollander | MIT |
|
||||
|
||||
The full license texts for these third-party files are included in the
|
||||
[LICENSE](LICENSE) file. The `eth-phishing-detect` row carries no repository
|
||||
link because the upstream is hosted under a competitor's organization name,
|
||||
which project policy keeps out of code and documentation; the vendored copy and
|
||||
the runtime refresh both come from that upstream, whose URL is the
|
||||
`BLOCKLIST_URL` constant in `src/shared/phishingDomains.js`.
|
||||
which project policy keeps out of code and documentation.
|
||||
`script/vendor-blocklist` is the single definition and the only file that spells
|
||||
the name in prose: it is build-time tooling, never shipped, and it records the
|
||||
exact URL, the commit it is pinned to and the sha256 of the bytes that commit
|
||||
serves, because a source reference nobody can verify is not a source reference.
|
||||
`script/check-censored` reads the name back out of that one file and fails the
|
||||
build wherever else it appears, save for two shipped-code literals it cannot
|
||||
avoid — each permitted only at the one path that carries it, and listed in that
|
||||
script's header.
|
||||
|
||||
## Author
|
||||
|
||||
|
||||
30
TODO.md
30
TODO.md
@@ -72,6 +72,29 @@ but the review is broader than any of them.
|
||||
the deletion of both persisted-value assignments in `settings.js` (only the
|
||||
selector round-trip case red)
|
||||
([#229](https://git.eeqj.de/sneak/AutistMask/issues/229)).
|
||||
- 2026-08-17: The phishing blocklist is vendored at build time and censored, and
|
||||
the runtime fetch is gone
|
||||
([#219](https://git.eeqj.de/sneak/AutistMask/issues/219)).
|
||||
`script/vendor-blocklist` fetches upstream at a pinned commit, verifies the
|
||||
sha256 of the bytes it was served, and writes
|
||||
`src/shared/phishingBlocklist.json` as truncated sha256 digests rather than
|
||||
domain names — which is what removes the competitor's name from a list that
|
||||
carried it 6,475 times, without dropping a single one of those domains.
|
||||
`script/check-censored` runs in `make check` and again against `dist/` at the
|
||||
end of every build, each permitted occurrence scoped to the one path allowed
|
||||
to carry it; the name now appears only in the vendoring script, which defines
|
||||
it once, in the provider-shim identifiers in `src/content/inpage.js`, and in
|
||||
one ERC-20's on-chain name in `src/shared/tokenList.js`. Removing the fetch
|
||||
retired the delta, the persistence and the 24-hour alarm from
|
||||
[#158](https://git.eeqj.de/sneak/AutistMask/issues/158), and retired alarms
|
||||
are now cleared rather than left running on existing installs. Two
|
||||
consequences, both deliberate: the list no longer self-updates, so it is as
|
||||
fresh as the last vendoring run that was released; and re-vendoring from
|
||||
current upstream took it from 231,357 stale entries to 105,721 current ones,
|
||||
because upstream prunes and the vendored snapshot never did. `dist/` fell from
|
||||
18.9 MB to 8.9 MB. The e2e suite now drives the warning end to end from a real
|
||||
blocklisted origin, and its service-worker interception canary has a new
|
||||
anchor, because the startup fetch it used to watch for no longer exists.
|
||||
- 2026-08-17: One wording for an empty password field on every screen that asks
|
||||
for one. The private key export screen said "Password is required." where the
|
||||
other five say "Please enter your password.", the same one-condition-two-
|
||||
@@ -100,9 +123,10 @@ but the review is broader than any of them.
|
||||
and coverage change, not a repair of a broken target. `storageGet()` and
|
||||
`storageSet()` **reject** where `storage.local` is absent rather than
|
||||
resolving `{}` and a no-op write — they carry the wallet, and defaulting would
|
||||
read an existing wallet back as none. The one caller that genuinely degrades,
|
||||
[`src/shared/phishingDomains.js`](src/shared/phishingDomains.js), takes
|
||||
`storageLocal()` directly and keeps its own null check.
|
||||
read an existing wallet back as none. The one caller that genuinely degraded,
|
||||
[`src/shared/phishingDomains.js`](src/shared/phishingDomains.js), took
|
||||
`storageLocal()` directly and kept its own null check; it stores nothing at
|
||||
all as of [#219](https://git.eeqj.de/sneak/AutistMask/issues/219) above.
|
||||
- 2026-08-17: An address total no longer reports `$0.00` for holdings it cannot
|
||||
price. Prices exist for the top 25 tokens only, so the priced-only sum was
|
||||
printed as the total and an address holding nothing but unpriced ERC-20s was
|
||||
|
||||
@@ -120,25 +120,6 @@ What gets sent: token symbol names (e.g. "ETH", "USDC"). No addresses, no
|
||||
balances, no identifying information. As with any request, CoinDesk sees your IP
|
||||
address.
|
||||
|
||||
**Phishing domain blocklist** (`raw.githubusercontent.com`)
|
||||
|
||||
A community-maintained list of phishing domains, used to warn you when a site
|
||||
that asks to connect, or to have a transaction or signature approved, is a known
|
||||
scam. A copy is bundled into the extension at build time, so the protection
|
||||
works before any network request happens. At runtime the extension fetches the
|
||||
live list to pick up newly added domains, keeping only the entries not already
|
||||
in the bundled copy (persisted locally if under 256 KiB). This endpoint is not
|
||||
user-configurable.
|
||||
|
||||
When it is contacted: when the background script starts, if the last fetch was
|
||||
more than 24 hours ago, and every 24 hours after that. The time of the last
|
||||
fetch is remembered across browser and background restarts, so restarting does
|
||||
not cause a re-download. If a fetch fails, or the list is too large to keep, the
|
||||
extension waits an hour before trying again outside that 24-hour schedule rather
|
||||
than retrying on every restart. It is a plain download of a public file —
|
||||
nothing about you is sent, but the host sees your IP address. If the fetch
|
||||
fails, the bundled copy is still used.
|
||||
|
||||
**Etherscan address labels** (`etherscan.io`; `sepolia.etherscan.io` on Sepolia)
|
||||
|
||||
When you review a send, AutistMask fetches the recipient's public Etherscan
|
||||
@@ -367,8 +348,12 @@ confirmation screen. It contains only addresses involved in fraud -- it is not a
|
||||
sanctions list.
|
||||
|
||||
**Phishing domain warnings.** Sites asking to connect or to have something
|
||||
approved are checked against the phishing domain blocklist described under
|
||||
External Services, and flagged with a red banner if they match.
|
||||
approved are checked against a community-maintained list of known phishing
|
||||
domains, and flagged with a red banner if they match. The list is built into the
|
||||
extension: the check is entirely local, so nobody is told which sites you visit,
|
||||
and it works offline. It is also only as current as the release you are running
|
||||
— a domain added to the list upstream reaches you in the next version of the
|
||||
extension, not the same day.
|
||||
|
||||
The first four filters can be individually disabled in Settings if you prefer to
|
||||
see everything unfiltered.
|
||||
|
||||
@@ -125,6 +125,16 @@ module.exports = [
|
||||
},
|
||||
},
|
||||
|
||||
// The helpers the script/ entrypoints call: plain node programs too, run
|
||||
// from a shell script rather than from yarn, and never bundled.
|
||||
{
|
||||
files: ["script/lib/**/*.js"],
|
||||
languageOptions: {
|
||||
...commonjs,
|
||||
globals: { ...globals.node },
|
||||
},
|
||||
},
|
||||
|
||||
// The e2e harnesses are node programs that also carry, inline, the
|
||||
// callbacks they ship into the browser via page.evaluate — so both
|
||||
// contexts really are present in the same file and both sets of globals
|
||||
|
||||
@@ -8,6 +8,7 @@ SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
|
||||
main() {
|
||||
"$SCRIPT_DIR/test"
|
||||
"$SCRIPT_DIR/test-verify-build"
|
||||
"$SCRIPT_DIR/check-censored"
|
||||
"$SCRIPT_DIR/lint"
|
||||
"$SCRIPT_DIR/fmt-check"
|
||||
}
|
||||
|
||||
301
script/check-censored
Executable file
301
script/check-censored
Executable file
@@ -0,0 +1,301 @@
|
||||
#!/bin/sh
|
||||
# script/check-censored: assert that the competitor name RULES.md bars appears
|
||||
# nowhere in this repo, and nowhere in the built extension, except where it is
|
||||
# deliberate. Our own extension to scripts-to-rule-them-all, run from
|
||||
# script/check and from make build.
|
||||
#
|
||||
# Where the name is allowed, and why each one is not negotiable away:
|
||||
#
|
||||
# - script/vendor-blocklist. Build-time tooling, never shipped. A pinned
|
||||
# source reference that does not say what the source is cannot be verified
|
||||
# by anyone, so it names it. Whole-file exemption.
|
||||
# - the two provider-shim identifiers in src/content/inpage.js. Protocol
|
||||
# identifiers dApps feature-detect on; renaming them does not rename them in
|
||||
# their code, it only stops this wallet working on their sites.
|
||||
# - the on-chain name of the MUSD ERC-20 in src/shared/tokenList.js. It is not
|
||||
# what backs symbol-spoof detection — that reads symbol and address — but
|
||||
# the wallet already surfaces the on-chain name of any token the user holds
|
||||
# (src/shared/balances.js), and this contract's on-chain name is that
|
||||
# string, so censoring the repo cannot stop the wallet displaying it.
|
||||
# Dropping the entry instead would cost the user MUSD spoof detection.
|
||||
#
|
||||
# Everything else fails, in the working tree and under dist/. The last two are
|
||||
# literals rather than whole files, so they are enforced by counting, and each
|
||||
# literal is scoped to the path allowed to carry it: a file may contain the name
|
||||
# only as many times as it contains the literals permitted *there*, and zero
|
||||
# times anywhere else. The emitted bundles carry them too, so a plain "the name
|
||||
# must not appear in dist/" could never have passed.
|
||||
#
|
||||
# The name itself is not written in this file. script/vendor-blocklist is the
|
||||
# one place in this repo that defines it, and this reads it back out of there —
|
||||
# so the repo-wide grep this check exists to enforce keeps returning exactly the
|
||||
# files named above, and this file is not one of them.
|
||||
set -eu
|
||||
|
||||
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
|
||||
|
||||
# Absolute path to this script, resolved before anything cd's anywhere: the
|
||||
# scan half runs in a re-invocation through xargs, so that the paths it works on
|
||||
# arrive as arguments and cannot be reshaped by field splitting on the way in.
|
||||
SELF="$(cd "$(dirname "$0")" && pwd -P)/$(basename "$0")"
|
||||
|
||||
# Internal re-entry flag. Not part of the command-line interface.
|
||||
SCAN_FLAG="--scan-paths"
|
||||
|
||||
VENDOR_SCRIPT="$ROOT/script/vendor-blocklist"
|
||||
|
||||
# Set by extract_name / make_literals_file.
|
||||
NAME=""
|
||||
ALLOWED_LITERALS_FILE=""
|
||||
|
||||
FAILED=0
|
||||
|
||||
cleanup() {
|
||||
[ -z "$ALLOWED_LITERALS_FILE" ] || rm -f "$ALLOWED_LITERALS_FILE"
|
||||
}
|
||||
trap cleanup EXIT INT TERM
|
||||
|
||||
fail() {
|
||||
echo "check-censored: FAIL: $*" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
# The name, taken from the single place that defines it. A check scanning for a
|
||||
# pattern it failed to read would pass against anything, so this refuses to
|
||||
# continue unless it got something that looks like the definition.
|
||||
extract_name() {
|
||||
[ -f "$VENDOR_SCRIPT" ] ||
|
||||
fail "$VENDOR_SCRIPT is missing, and it is where the name being
|
||||
checked for is defined. Nothing was scanned."
|
||||
|
||||
NAME="$(grep -m1 '^UPSTREAM_ORG=' "$VENDOR_SCRIPT" | cut -d'"' -f2)" ||
|
||||
fail "could not read UPSTREAM_ORG from $VENDOR_SCRIPT. Nothing was
|
||||
scanned."
|
||||
|
||||
case "$NAME" in
|
||||
"" | *[!A-Za-z0-9]*)
|
||||
fail "UPSTREAM_ORG in $VENDOR_SCRIPT did not yield a plain name
|
||||
(got: '$NAME'). Scanning for that would prove nothing. Nothing was
|
||||
scanned."
|
||||
;;
|
||||
esac
|
||||
}
|
||||
|
||||
make_literals_file() {
|
||||
ALLOWED_LITERALS_FILE="$(mktemp \
|
||||
"${TMPDIR:-/tmp}/autistmask-censored.XXXXXX")" ||
|
||||
fail "could not create a temporary file, so nothing was scanned."
|
||||
}
|
||||
|
||||
# The literals $1 may carry, and nothing else may. Each contains the name
|
||||
# exactly once, which is what makes counting them sound; each is scoped to its
|
||||
# path, so a file with no business carrying the name fails even when it spells
|
||||
# it the way shipped code has to. Scoping is the point: permitting these
|
||||
# literals in any file is what once let this check pass its own prose.
|
||||
#
|
||||
# The emitted paths are listed next to the sources they come from. If the
|
||||
# bundler moves one, this goes red and the new path gets added deliberately,
|
||||
# rather than a wildcard over dist/ covering whatever lands there.
|
||||
allowed_literals_for() {
|
||||
: >"$ALLOWED_LITERALS_FILE"
|
||||
case "$1" in
|
||||
src/content/inpage.js | dist/*/src/content/inpage.js)
|
||||
printf 'is%s\n_%s\n' "$NAME" "$NAME" >"$ALLOWED_LITERALS_FILE"
|
||||
;;
|
||||
src/shared/tokenList.js | dist/*/src/background/index.js | \
|
||||
dist/*/src/popup/index.js)
|
||||
printf '%s USD\n' "$NAME" >"$ALLOWED_LITERALS_FILE"
|
||||
;;
|
||||
esac
|
||||
}
|
||||
|
||||
# How many times does $1 contain the name (TOTAL), and how many of those are one
|
||||
# of the allowed literals (ALLOWED)? Same discipline the rest of this repo's
|
||||
# shell checks apply to grep: exit 0 and 1 are answers about the file, anything
|
||||
# else means the file was not searched and is not an answer at all.
|
||||
count_matches() {
|
||||
_cm_status=0
|
||||
_cm_out="$(grep -a -o -i -F -e "$NAME" -- "$1")" || _cm_status=$?
|
||||
case "$_cm_status" in
|
||||
0) TOTAL="$(printf '%s\n' "$_cm_out" | grep -c .)" ;;
|
||||
1) TOTAL=0 ;;
|
||||
*)
|
||||
fail "grep exited $_cm_status reading $1, so the file was never
|
||||
searched and nothing was established about it. That is a permissions or I/O
|
||||
fault, not a clean file. Refusing to report success."
|
||||
;;
|
||||
esac
|
||||
|
||||
if [ "$TOTAL" -eq 0 ]; then
|
||||
ALLOWED=0
|
||||
return 0
|
||||
fi
|
||||
|
||||
# No literal is permitted at this path, so every occurrence is a violation.
|
||||
# Handled here rather than by grep, which is not required to say anything
|
||||
# useful about an empty pattern file.
|
||||
if [ ! -s "$ALLOWED_LITERALS_FILE" ]; then
|
||||
ALLOWED=0
|
||||
return 0
|
||||
fi
|
||||
|
||||
_cm_status=0
|
||||
_cm_out="$(grep -a -o -i -F -f "$ALLOWED_LITERALS_FILE" -- "$1")" ||
|
||||
_cm_status=$?
|
||||
case "$_cm_status" in
|
||||
0) ALLOWED="$(printf '%s\n' "$_cm_out" | grep -c .)" ;;
|
||||
1) ALLOWED=0 ;;
|
||||
*)
|
||||
fail "grep exited $_cm_status matching the allowed literals in $1.
|
||||
Refusing to report success."
|
||||
;;
|
||||
esac
|
||||
}
|
||||
|
||||
# The per-path half, run in a re-invocation of this script so it uses the same
|
||||
# counting as everything else rather than a second copy of it.
|
||||
scan_paths() {
|
||||
for _file in "$@"; do
|
||||
# dist/ arrives absolute (find) and the worktree relative (git
|
||||
# ls-files). The allowlist is keyed on repo-relative paths, so both
|
||||
# forms are reduced to one before anything is decided about them.
|
||||
_rel="$_file"
|
||||
case "$_rel" in
|
||||
"$ROOT"/*) _rel="${_rel#"$ROOT"/}" ;;
|
||||
esac
|
||||
|
||||
case "$_rel" in
|
||||
script/vendor-blocklist) continue ;;
|
||||
esac
|
||||
[ -f "$_file" ] || continue
|
||||
|
||||
allowed_literals_for "$_rel"
|
||||
count_matches "$_file"
|
||||
[ "$TOTAL" -gt "$ALLOWED" ] || continue
|
||||
|
||||
FAILED=$((FAILED + 1))
|
||||
echo "check-censored: $_rel: $TOTAL occurrence(s) of the name," \
|
||||
"$ALLOWED of them allowed at this path" >&2
|
||||
grep -a -n -i -F -e "$NAME" -- "$_file" | cut -c1-140 | head -5 >&2
|
||||
done
|
||||
[ "$FAILED" -eq 0 ]
|
||||
}
|
||||
|
||||
# Hand a NUL-delimited listing to the scan half. Returns non-zero if any path
|
||||
# failed, or if the scan could not be run at all.
|
||||
scan_listing() {
|
||||
xargs -0 "$SELF" "$SCAN_FLAG" <"$1"
|
||||
}
|
||||
|
||||
# Every file git tracks, plus everything untracked and not ignored: the working
|
||||
# tree as a reviewer would see it, and never node_modules or dist/ (both are
|
||||
# ignored; dist/ is walked separately below).
|
||||
check_worktree() {
|
||||
_list="$(mktemp "${TMPDIR:-/tmp}/autistmask-censored-tree.XXXXXX")" ||
|
||||
fail "could not create a temporary file, so nothing was scanned."
|
||||
_status=0
|
||||
git ls-files -z --cached --others --exclude-standard >"$_list" ||
|
||||
_status=$?
|
||||
[ "$_status" -eq 0 ] || {
|
||||
rm -f "$_list"
|
||||
fail "git ls-files exited $_status, so the working tree was never
|
||||
enumerated and nothing was established about it."
|
||||
}
|
||||
|
||||
# Repo-relative paths. The scan half cd's to the repo root before it opens
|
||||
# anything, so they reach it intact and unjoined.
|
||||
WORKTREE_COUNT="$(tr -dc '\0' <"$_list" | wc -c | tr -d ' ')"
|
||||
|
||||
_status=0
|
||||
scan_listing "$_list" || _status=$?
|
||||
rm -f "$_list"
|
||||
return "$_status"
|
||||
}
|
||||
|
||||
check_dist() {
|
||||
_list="$(mktemp "${TMPDIR:-/tmp}/autistmask-censored-dist.XXXXXX")" ||
|
||||
fail "could not create a temporary file, so dist/ was not scanned."
|
||||
_status=0
|
||||
find "$ROOT/dist" -type f -print0 >"$_list" || _status=$?
|
||||
[ "$_status" -eq 0 ] || {
|
||||
rm -f "$_list"
|
||||
fail "find exited $_status enumerating dist/, so part of the emitted
|
||||
tree was never walked and an unchecked file there went unchecked. Refusing
|
||||
to report success."
|
||||
}
|
||||
|
||||
DIST_COUNT="$(tr -dc '\0' <"$_list" | wc -c | tr -d ' ')"
|
||||
|
||||
_status=0
|
||||
scan_listing "$_list" || _status=$?
|
||||
rm -f "$_list"
|
||||
return "$_status"
|
||||
}
|
||||
|
||||
usage() {
|
||||
echo "usage: script/check-censored [--require-dist]" >&2
|
||||
exit 2
|
||||
}
|
||||
|
||||
main() {
|
||||
cd "$ROOT"
|
||||
|
||||
# Internal re-entry from scan_listing's xargs.
|
||||
if [ "${1-}" = "$SCAN_FLAG" ]; then
|
||||
shift
|
||||
extract_name
|
||||
make_literals_file
|
||||
scan_paths "$@"
|
||||
return $?
|
||||
fi
|
||||
|
||||
require_dist=no
|
||||
case "${1-}" in
|
||||
"") ;;
|
||||
--require-dist) require_dist=yes ;;
|
||||
*) usage ;;
|
||||
esac
|
||||
|
||||
extract_name
|
||||
make_literals_file
|
||||
|
||||
echo "Checking for censored names..."
|
||||
|
||||
tree_status=0
|
||||
check_worktree || tree_status=$?
|
||||
|
||||
dist_status=0
|
||||
dist_inspected=no
|
||||
DIST_COUNT=0
|
||||
if [ -d "$ROOT/dist" ]; then
|
||||
dist_inspected=yes
|
||||
check_dist || dist_status=$?
|
||||
fi
|
||||
|
||||
if [ "$tree_status" -ne 0 ] || [ "$dist_status" -ne 0 ]; then
|
||||
fail "the name appears outside the deliberate exceptions (reported
|
||||
above). See the header of script/check-censored for what is allowed and
|
||||
why."
|
||||
fi
|
||||
|
||||
if [ "$dist_inspected" = no ]; then
|
||||
if [ "$require_dist" = yes ]; then
|
||||
fail "there is no dist/ to inspect and this run was asked to
|
||||
require one. Run make build."
|
||||
fi
|
||||
cat <<EOF
|
||||
################################################################################
|
||||
## WARNING: dist/ WAS NOT INSPECTED BY THIS RUN AND IS NOT PROVEN CLEAN BY IT.
|
||||
## There is no dist/ in this tree. The working tree is clean, but a build can
|
||||
## carry text no source file does — a dependency's, or a bundler's. Every
|
||||
## make build runs this check again with dist/ required, so a release artifact
|
||||
## is always covered; this run simply had none to look at.
|
||||
################################################################################
|
||||
EOF
|
||||
fi
|
||||
|
||||
echo "check-censored: $WORKTREE_COUNT tracked file(s) inspected," \
|
||||
"$DIST_COUNT file(s) under dist/"
|
||||
}
|
||||
|
||||
main "$@"
|
||||
147
script/lib/build-blocklist.js
Normal file
147
script/lib/build-blocklist.js
Normal file
@@ -0,0 +1,147 @@
|
||||
// The transform half of script/vendor-blocklist: upstream's config.json in,
|
||||
// src/shared/phishingBlocklist.json out. Build-time repo tooling; nothing here
|
||||
// is shipped to users.
|
||||
//
|
||||
// Usage: node script/lib/build-blocklist.js <source.json> <output.json>
|
||||
//
|
||||
// What it does, and why each step is here:
|
||||
//
|
||||
// - only the blacklist is carried over. The extension matches a hostname and
|
||||
// its parent domains against that one list; upstream's whitelist, fuzzylist
|
||||
// and version metadata are read by nothing here, so shipping them would add
|
||||
// megabytes of dead weight to every install.
|
||||
// - entries are lowercased and de-duplicated, because that is the form
|
||||
// isPhishingDomain() compares against.
|
||||
// - entries that cannot be a hostname are dropped and counted. Upstream
|
||||
// carries the odd URL-shaped entry (a path, a scheme); hostname matching can
|
||||
// never match one, and once the artifact is hashes nobody can see that it is
|
||||
// in there, so it is reported at vendoring time instead.
|
||||
// - entries are hashed (see src/shared/domainHash.js) and sorted, and the
|
||||
// digests are concatenated into one fixed-width string. Sorted is what makes
|
||||
// the runtime lookup a binary search over that string, with no set to build
|
||||
// on every service-worker wake; one string rather than an array of 100k+ is
|
||||
// what keeps the file, the bundle and the JSON parse small.
|
||||
//
|
||||
// Deterministic by construction: same input bytes, same output bytes.
|
||||
|
||||
"use strict";
|
||||
|
||||
const fs = require("fs");
|
||||
|
||||
const {
|
||||
HASH_ALGORITHM,
|
||||
HASH_HEX_CHARS,
|
||||
hashDomain,
|
||||
} = require("../../src/shared/domainHash");
|
||||
|
||||
// A blocklist that has collapsed to a handful of entries is a broken fetch or a
|
||||
// changed upstream shape, not a quiet day in phishing. Vendoring it would
|
||||
// disarm the feature, so it fails instead and a human decides.
|
||||
const MIN_ENTRIES = 10000;
|
||||
|
||||
function fail(message) {
|
||||
process.stderr.write("build-blocklist: " + message + "\n");
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// A hostname, as the matcher understands one: dot-separated labels of letters,
|
||||
// digits, hyphens and underscores. Anything else — a path, a scheme, a space,
|
||||
// an empty string, a non-ASCII label a browser would have punycoded before it
|
||||
// ever reached isPhishingDomain() — cannot be produced by the hostname variants
|
||||
// the extension looks up, so it could only ever sit in the artifact unused.
|
||||
//
|
||||
// Underscores are deliberate. They are not legal in a hostname per RFC 1123,
|
||||
// but DNS carries them and browsers resolve them, and upstream lists 141 entries
|
||||
// that use one — real phishing sites on shared subdomain hosts. A stricter
|
||||
// pattern silently drops every one of them.
|
||||
const HOSTNAME_RE =
|
||||
/^[a-z0-9_]([a-z0-9_-]*[a-z0-9_])?(\.[a-z0-9_]([a-z0-9_-]*[a-z0-9_])?)+$/;
|
||||
|
||||
function main(argv) {
|
||||
const [source, output] = argv;
|
||||
if (!source || !output) {
|
||||
fail("usage: build-blocklist.js <source.json> <output.json>");
|
||||
}
|
||||
|
||||
let config;
|
||||
try {
|
||||
config = JSON.parse(fs.readFileSync(source, "utf8"));
|
||||
} catch (e) {
|
||||
fail("could not read " + source + " as JSON: " + e.message);
|
||||
}
|
||||
|
||||
if (!Array.isArray(config.blacklist)) {
|
||||
fail(
|
||||
"the source has no blacklist array, so its shape is not the one " +
|
||||
"this transform understands. Refusing to write an artifact.",
|
||||
);
|
||||
}
|
||||
|
||||
const seen = new Set();
|
||||
let dropped = 0;
|
||||
for (const raw of config.blacklist) {
|
||||
if (typeof raw !== "string") {
|
||||
dropped++;
|
||||
continue;
|
||||
}
|
||||
const domain = raw.trim().toLowerCase();
|
||||
if (!HOSTNAME_RE.test(domain)) {
|
||||
dropped++;
|
||||
continue;
|
||||
}
|
||||
seen.add(domain);
|
||||
}
|
||||
|
||||
if (seen.size < MIN_ENTRIES) {
|
||||
fail(
|
||||
"the source yielded " +
|
||||
seen.size +
|
||||
" usable entries, below the " +
|
||||
MIN_ENTRIES +
|
||||
" floor. That is a broken source or a changed upstream " +
|
||||
"shape, and vendoring it would disarm phishing detection. " +
|
||||
"Refusing to write an artifact.",
|
||||
);
|
||||
}
|
||||
|
||||
const hashes = [];
|
||||
for (const domain of seen) hashes.push(hashDomain(domain));
|
||||
hashes.sort();
|
||||
|
||||
// Truncation makes collisions possible; they are harmless (both entries are
|
||||
// blocked either way) but they must not inflate the count the artifact
|
||||
// claims, which the runtime cross-checks against the string length.
|
||||
const unique = [];
|
||||
for (const hash of hashes) {
|
||||
if (unique.length === 0 || unique[unique.length - 1] !== hash) {
|
||||
unique.push(hash);
|
||||
}
|
||||
}
|
||||
|
||||
const artifact = {
|
||||
algorithm: HASH_ALGORITHM,
|
||||
hashHexChars: HASH_HEX_CHARS,
|
||||
count: unique.length,
|
||||
hashes: unique.join(""),
|
||||
};
|
||||
|
||||
// Four-space JSON with a trailing newline: what prettier emits for this
|
||||
// shape, so a vendored artifact passes make fmt-check untouched.
|
||||
fs.writeFileSync(output, JSON.stringify(artifact, null, 4) + "\n");
|
||||
|
||||
process.stdout.write(
|
||||
"build-blocklist: " +
|
||||
config.blacklist.length +
|
||||
" source entries -> " +
|
||||
seen.size +
|
||||
" usable domains -> " +
|
||||
unique.length +
|
||||
" digests (" +
|
||||
dropped +
|
||||
" not hostnames, " +
|
||||
(seen.size - unique.length) +
|
||||
" digest collisions)\n",
|
||||
);
|
||||
}
|
||||
|
||||
main(process.argv.slice(2));
|
||||
@@ -59,12 +59,12 @@ main() {
|
||||
# browser profile.
|
||||
# PW_EXPERIMENTAL_SERVICE_WORKER_NETWORK_EVENTS=1: without it,
|
||||
# ctx.route() intercepts page requests only, and every fetch made by
|
||||
# the MV3 background service worker — including the phishing
|
||||
# blocklist fetch that src/background/index.js issues at worker
|
||||
# startup — goes to the real internet. The flag is experimental and
|
||||
# Playwright may drop or rename it. It cannot break silently: the
|
||||
# harness probes service-worker interception at launch and aborts
|
||||
# the whole suite if it is not in effect (see the interception
|
||||
# the MV3 background service worker — the JSON-RPC calls behind
|
||||
# every approval the suite drives among them — goes to the real
|
||||
# internet. The flag is experimental and Playwright may drop or
|
||||
# rename it. It cannot break silently: the harness asks the worker
|
||||
# for one request of its own at launch and aborts the whole suite
|
||||
# if it does not reach the route handler (see the interception
|
||||
# canary in tests/e2e/harness.js). If a future Playwright removes
|
||||
# the flag, that probe is what will fail, and the fix is either a
|
||||
# replacement mechanism or an honest downgrade of the isolation
|
||||
|
||||
105
script/vendor-blocklist
Executable file
105
script/vendor-blocklist
Executable file
@@ -0,0 +1,105 @@
|
||||
#!/bin/sh
|
||||
# script/vendor-blocklist: refresh the vendored phishing blocklist at
|
||||
# src/shared/phishingBlocklist.json from its upstream source. Our own extension
|
||||
# to scripts-to-rule-them-all.
|
||||
#
|
||||
# This is build-time repo tooling and is not shipped. It is the one place in
|
||||
# this repo that names the upstream project, because a source reference that
|
||||
# does not say what the source is cannot be verified by anyone; the artifact it
|
||||
# writes carries no names at all (see src/shared/domainHash.js).
|
||||
# script/check-censored reads the name back out of this file rather than
|
||||
# repeating it, so it stays defined exactly once.
|
||||
#
|
||||
# Run it deliberately, not on every build: the output is committed, and the
|
||||
# extension does no runtime fetching, so the shipped list is exactly as fresh as
|
||||
# the last time someone ran this and landed the result. Re-run it, land the
|
||||
# diff, cut a release; that is the whole refresh path.
|
||||
#
|
||||
# Pinned by content hash, twice over, as REPO_POLICIES.md requires. The commit
|
||||
# below is an immutable ref — the upstream default branch moves several times a
|
||||
# day and cannot be pinned — and UPSTREAM_SHA256 is the sha256 of the bytes that
|
||||
# commit serves. A mismatch is a hard failure: a vendoring step that accepts
|
||||
# whatever it is handed is a supply-chain hole, and this one feeds a security
|
||||
# warning shown to users.
|
||||
#
|
||||
# To move the pin: pick the new commit, run this with the new UPSTREAM_COMMIT
|
||||
# and an UPSTREAM_SHA256 you have not yet updated, and it will print the hash it
|
||||
# actually got. Verify that hash against the source independently before
|
||||
# recording it. Never copy the "actual" line in on trust.
|
||||
set -eu
|
||||
|
||||
ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
|
||||
|
||||
# Upstream, pinned 2026-08-17.
|
||||
UPSTREAM_ORG="MetaMask"
|
||||
UPSTREAM_REPO="eth-phishing-detect"
|
||||
UPSTREAM_COMMIT="6dddf74a87da3e1a0841f7ae0d1cb31aaf2c05db"
|
||||
UPSTREAM_FILE="src/config.json"
|
||||
UPSTREAM_SHA256="166d5b3504e8f4ed52eae37d3dd20c1a56efa0502bfb3dc957044ff8b5f1283f"
|
||||
|
||||
OUTPUT="src/shared/phishingBlocklist.json"
|
||||
|
||||
WORK=""
|
||||
|
||||
cleanup() {
|
||||
[ -z "$WORK" ] || rm -rf "$WORK"
|
||||
}
|
||||
trap cleanup EXIT INT TERM
|
||||
|
||||
fail() {
|
||||
echo "vendor-blocklist: $*" >&2
|
||||
exit 1
|
||||
}
|
||||
|
||||
sha256_of() {
|
||||
if command -v sha256sum >/dev/null 2>&1; then
|
||||
sha256sum "$1" | cut -d' ' -f1
|
||||
elif command -v shasum >/dev/null 2>&1; then
|
||||
shasum -a 256 "$1" | cut -d' ' -f1
|
||||
else
|
||||
fail "neither sha256sum nor shasum is available, so the fetched
|
||||
source cannot be verified. Refusing to vendor unverified content."
|
||||
fi
|
||||
}
|
||||
|
||||
main() {
|
||||
cd "$ROOT"
|
||||
|
||||
command -v curl >/dev/null 2>&1 ||
|
||||
fail "curl is required to fetch the upstream list"
|
||||
command -v node >/dev/null 2>&1 ||
|
||||
fail "node is required to build the artifact; run script/bootstrap"
|
||||
|
||||
WORK="$(mktemp -d "${TMPDIR:-/tmp}/autistmask-vendor-blocklist.XXXXXX")" ||
|
||||
fail "could not create a working directory"
|
||||
|
||||
url="https://raw.githubusercontent.com/$UPSTREAM_ORG/$UPSTREAM_REPO/$UPSTREAM_COMMIT/$UPSTREAM_FILE"
|
||||
echo "Fetching $url"
|
||||
curl -fsSL --proto '=https' --tlsv1.2 -o "$WORK/source.json" "$url" ||
|
||||
fail "the fetch failed, so nothing was vendored"
|
||||
|
||||
actual="$(sha256_of "$WORK/source.json")"
|
||||
if [ "$actual" != "$UPSTREAM_SHA256" ]; then
|
||||
fail "sha256 mismatch on the fetched source.
|
||||
expected: $UPSTREAM_SHA256
|
||||
actual: $actual
|
||||
The pinned commit is immutable, so the same commit serving different bytes
|
||||
means the content was substituted somewhere between upstream and here.
|
||||
Nothing was written. Do not update the expectation to match unless you have
|
||||
verified the new bytes independently."
|
||||
fi
|
||||
echo "Verified sha256 $actual"
|
||||
|
||||
node script/lib/build-blocklist.js "$WORK/source.json" "$WORK/out.json" ||
|
||||
fail "the transform failed, so nothing was written"
|
||||
|
||||
if [ -f "$OUTPUT" ] && cmp -s "$WORK/out.json" "$OUTPUT"; then
|
||||
echo "vendor-blocklist: $OUTPUT is already up to date"
|
||||
return 0
|
||||
fi
|
||||
|
||||
cp "$WORK/out.json" "$OUTPUT"
|
||||
echo "vendor-blocklist: wrote $OUTPUT (sha256 $(sha256_of "$OUTPUT"))"
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -27,14 +27,9 @@ const {
|
||||
TX_STAGE_NONCE,
|
||||
} = require("../shared/approvalVerify");
|
||||
const { prepareApprovalTx } = require("../shared/approvalTx");
|
||||
const {
|
||||
isPhishingDomain,
|
||||
refreshPhishingListOnSchedule,
|
||||
initPhishingList,
|
||||
} = require("../shared/phishingDomains");
|
||||
const { isPhishingDomain } = require("../shared/phishingDomains");
|
||||
const {
|
||||
BALANCE_REFRESH_ALARM,
|
||||
PHISHING_REFRESH_ALARM,
|
||||
BALANCE_REFRESH_PERIOD_MINUTES,
|
||||
ensureRecurringAlarms,
|
||||
registerAlarmHandlers,
|
||||
@@ -1052,26 +1047,20 @@ async function backgroundRefresh() {
|
||||
await saveState();
|
||||
}
|
||||
|
||||
// Both recurring jobs run off alarms, not timers. On Chrome MV3 this file is
|
||||
// The recurring job runs off an alarm, not a timer. On Chrome MV3 this file is
|
||||
// a service worker that the browser terminates after about 30 seconds idle,
|
||||
// so a setInterval would only ever survive until the first idle period and
|
||||
// module-level state does not outlive it. Alarms are held by the browser and
|
||||
// wake the worker to deliver them.
|
||||
registerAlarmHandlers({
|
||||
[BALANCE_REFRESH_ALARM]: backgroundRefresh,
|
||||
// The scheduled refresh, which restores persisted state on a freshly
|
||||
// revived worker and then fetches unconditionally. The freshness guards
|
||||
// belong to the startup path; applying them here would make the tick skip
|
||||
// itself.
|
||||
[PHISHING_REFRESH_ALARM]: refreshPhishingListOnSchedule,
|
||||
});
|
||||
|
||||
// Everything the background context needs re-established on start. This runs
|
||||
// on a fresh install, on browser startup, and on every revival of a
|
||||
// terminated worker, so it must be idempotent: ensureRecurringAlarms() only
|
||||
// creates alarms that are missing or carrying a stale period, and
|
||||
// initPhishingList() fetches only when the persisted timestamps say the list
|
||||
// is stale.
|
||||
// creates alarms that are missing or carrying a stale period, and only clears
|
||||
// retired ones that are still registered.
|
||||
//
|
||||
// On a fresh install the top-level call and the onInstalled listener both run,
|
||||
// close enough together that both could see an alarm missing and create it.
|
||||
@@ -1082,10 +1071,7 @@ let backgroundJobsRun = null;
|
||||
|
||||
function startBackgroundJobs() {
|
||||
if (backgroundJobsRun) return backgroundJobsRun;
|
||||
backgroundJobsRun = Promise.all([
|
||||
ensureRecurringAlarms(),
|
||||
initPhishingList(),
|
||||
])
|
||||
backgroundJobsRun = ensureRecurringAlarms()
|
||||
.catch((err) => {
|
||||
// An alarm that failed to schedule means a recurring job silently
|
||||
// never runs again; it must not be an unhandled rejection.
|
||||
|
||||
@@ -179,7 +179,8 @@
|
||||
return this;
|
||||
},
|
||||
|
||||
// Some dApps (wagmi) check this to confirm MetaMask-like behavior
|
||||
// Some dApps (wagmi) probe this object to decide whether the provider
|
||||
// supports the de-facto standard extras. The name is theirs, not ours.
|
||||
_metamask: {
|
||||
isUnlocked() {
|
||||
return Promise.resolve(provider.selectedAddress !== null);
|
||||
|
||||
@@ -17,16 +17,26 @@
|
||||
// run finished and the alarm fires one run-duration earlier than that. Every
|
||||
// guard must therefore either be strictly shorter than the period it gates or
|
||||
// be bypassed on the scheduled tick — see backgroundRefresh() in
|
||||
// src/background/index.js and updatePhishingList() in shared/phishingDomains.js.
|
||||
// src/background/index.js.
|
||||
|
||||
const { alarmsApi } = require("./browserApi");
|
||||
|
||||
const BALANCE_REFRESH_ALARM = "autistmask-balance-refresh";
|
||||
const PHISHING_REFRESH_ALARM = "autistmask-phishing-refresh";
|
||||
|
||||
// Alarms this extension used to create and no longer has a handler for. A
|
||||
// browser keeps an alarm until something clears it, so a job that is deleted
|
||||
// from the code goes on waking the service worker on its old schedule forever,
|
||||
// on every install that ever ran the version which created it. Removing the job
|
||||
// means removing the alarm, so retired names are listed here and cleared on
|
||||
// every start until the installs that carry them are long gone.
|
||||
const OBSOLETE_ALARMS = [
|
||||
// The 24-hour phishing blocklist refresh, retired when the runtime fetch
|
||||
// was removed and the list became purely build-time vendored.
|
||||
"autistmask-phishing-refresh",
|
||||
];
|
||||
|
||||
const MIN_ALARM_PERIOD_MINUTES = 1;
|
||||
const BALANCE_REFRESH_PERIOD_MINUTES = 1;
|
||||
const PHISHING_REFRESH_PERIOD_MINUTES = 24 * 60;
|
||||
|
||||
// alarmsApi() resolves on use rather than at module load: the worker is torn
|
||||
// down and re-evaluated repeatedly, and tests install a stub after requiring
|
||||
@@ -65,22 +75,34 @@ async function ensureAlarm(name, periodInMinutes) {
|
||||
}
|
||||
|
||||
/**
|
||||
* Ensure both recurring background jobs are scheduled. Safe to call on every
|
||||
* worker start, on onInstalled and on onStartup.
|
||||
* Clear every alarm this extension no longer handles.
|
||||
*
|
||||
* @returns {Promise<{balance: boolean, phishing: boolean}>} which alarms this
|
||||
* call had to create.
|
||||
* @returns {Promise<string[]>} the retired alarms this call actually cleared.
|
||||
*/
|
||||
async function clearObsoleteAlarms() {
|
||||
const api = alarmsApi();
|
||||
if (!api || !api.clear) return [];
|
||||
const cleared = [];
|
||||
for (const name of OBSOLETE_ALARMS) {
|
||||
if (await api.clear(name)) cleared.push(name);
|
||||
}
|
||||
return cleared;
|
||||
}
|
||||
|
||||
/**
|
||||
* Ensure the recurring background jobs are scheduled, and that retired ones are
|
||||
* not. Safe to call on every worker start, on onInstalled and on onStartup.
|
||||
*
|
||||
* @returns {Promise<{balance: boolean, cleared: string[]}>} which alarms this
|
||||
* call had to create, and which retired ones it removed.
|
||||
*/
|
||||
async function ensureRecurringAlarms() {
|
||||
const balance = await ensureAlarm(
|
||||
BALANCE_REFRESH_ALARM,
|
||||
BALANCE_REFRESH_PERIOD_MINUTES,
|
||||
);
|
||||
const phishing = await ensureAlarm(
|
||||
PHISHING_REFRESH_ALARM,
|
||||
PHISHING_REFRESH_PERIOD_MINUTES,
|
||||
);
|
||||
return { balance, phishing };
|
||||
const cleared = await clearObsoleteAlarms();
|
||||
return { balance, cleared };
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -102,10 +124,10 @@ function registerAlarmHandlers(handlers) {
|
||||
|
||||
module.exports = {
|
||||
BALANCE_REFRESH_ALARM,
|
||||
PHISHING_REFRESH_ALARM,
|
||||
OBSOLETE_ALARMS,
|
||||
MIN_ALARM_PERIOD_MINUTES,
|
||||
BALANCE_REFRESH_PERIOD_MINUTES,
|
||||
PHISHING_REFRESH_PERIOD_MINUTES,
|
||||
clearObsoleteAlarms,
|
||||
ensureAlarm,
|
||||
ensureRecurringAlarms,
|
||||
registerAlarmHandlers,
|
||||
|
||||
41
src/shared/domainHash.js
Normal file
41
src/shared/domainHash.js
Normal file
@@ -0,0 +1,41 @@
|
||||
// The one definition of how a domain becomes a blocklist entry.
|
||||
//
|
||||
// The vendored phishing blocklist ships digests, not domain names: see
|
||||
// phishingDomains.js for why, and script/vendor-blocklist for how the artifact
|
||||
// is produced. Both sides have to agree exactly — a mismatch would silently
|
||||
// match nothing, which is a blocklist that quietly protects no one — so the
|
||||
// rule lives here and is required by both rather than written down twice.
|
||||
//
|
||||
// sha256 truncated to 64 bits. Truncation is what keeps the artifact small
|
||||
// enough to bundle (16 hex characters per entry rather than 64), and 64 bits is
|
||||
// far past what this has to withstand: over ~10^5 entries the chance that any
|
||||
// hostname a user visits collides with an entry it is not is about 10^-14 per
|
||||
// lookup, and a deliberate collision buys an attacker a false phishing warning
|
||||
// on a site they do not control, not a missed one. For scale, Safe Browsing
|
||||
// distributes 32-bit prefixes and resolves the rest against a server; this is
|
||||
// 32 bits more, with no server involved.
|
||||
|
||||
const { sha256, toUtf8Bytes } = require("ethers");
|
||||
|
||||
const HASH_ALGORITHM = "sha256";
|
||||
const HASH_HEX_CHARS = 16;
|
||||
|
||||
/**
|
||||
* The blocklist entry for a domain: lowercased, hashed, truncated.
|
||||
*
|
||||
* @param {string} domain
|
||||
* @returns {string} HASH_HEX_CHARS lowercase hex characters, no 0x prefix.
|
||||
*/
|
||||
function hashDomain(domain) {
|
||||
// ethers returns "0x" + 64 hex characters.
|
||||
return sha256(toUtf8Bytes(domain.toLowerCase())).slice(
|
||||
2,
|
||||
2 + HASH_HEX_CHARS,
|
||||
);
|
||||
}
|
||||
|
||||
module.exports = {
|
||||
HASH_ALGORITHM,
|
||||
HASH_HEX_CHARS,
|
||||
hashDomain,
|
||||
};
|
||||
@@ -4,8 +4,7 @@
|
||||
//
|
||||
// POPUP ONLY. localStorage does not exist in the Chrome MV3 service worker,
|
||||
// so this module must not be pulled into src/background/. Anything the
|
||||
// background context needs to cache goes in extension storage instead (see
|
||||
// shared/phishingDomains.js).
|
||||
// background context needs to cache goes in extension storage instead.
|
||||
|
||||
const { getProvider } = require("./balances");
|
||||
const { log } = require("./log");
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -1,158 +1,109 @@
|
||||
// Domain-based phishing detection using a vendored blocklist with delta updates.
|
||||
// Domain-based phishing detection against a blocklist vendored at build time.
|
||||
//
|
||||
// A community-maintained phishing domain blocklist is vendored in
|
||||
// phishingBlocklist.json and bundled at build time. At runtime, we fetch
|
||||
// the live list periodically and keep only the delta (new entries not in
|
||||
// the vendored list) in memory. This keeps runtime memory usage small.
|
||||
// The list is produced by script/vendor-blocklist from a hash-pinned upstream
|
||||
// commit, committed as phishingBlocklist.json, and bundled. There is no runtime
|
||||
// fetch: the extension asks nobody anything to answer this question, so no third
|
||||
// party learns which sites a user connects to, and no third party decides what
|
||||
// this wallet warns about. The cost is staleness — the shipped list is exactly
|
||||
// as fresh as the last vendoring run that was released — and the refresh path is
|
||||
// re-running that script and shipping the diff.
|
||||
//
|
||||
// The domain-checker checks the in-memory delta first (fresh/recent scam
|
||||
// sites), then falls back to the vendored list.
|
||||
// The artifact holds digests, not domains: sha256 truncated to 64 bits, one
|
||||
// entry per 16 hex characters, concatenated in sorted order into a single
|
||||
// string (see domainHash.js). Three things follow from that shape, and all
|
||||
// three are the reason for it:
|
||||
//
|
||||
// If the delta and its fetch timestamp fit in 256 KiB they are persisted to
|
||||
// extension storage, so they survive termination of the MV3 service worker.
|
||||
// Extension storage, not localStorage: localStorage does not exist in a
|
||||
// service worker, so the previous persistence never ran on Chrome at all.
|
||||
// The stored timestamps are what keep a restarted worker from re-fetching on
|
||||
// every wake while still noticing an overdue update. Those guards apply to the
|
||||
// startup path only; the 24-hour alarm tick bypasses them, or it would veto
|
||||
// its own refresh — see updatePhishingList().
|
||||
// - the extension ships no plaintext list of anyone's domain names, which is
|
||||
// what makes a blocklist assembled elsewhere shippable here at all.
|
||||
// - a lookup is a binary search over that string. Nothing is built at module
|
||||
// load, which matters because the MV3 service worker is torn down when idle
|
||||
// and re-evaluates this file on every wake.
|
||||
// - the file is 1.7 MB rather than 8.7 MB.
|
||||
//
|
||||
// Nothing here is async: callers answer an approval prompt with the result.
|
||||
|
||||
const vendoredConfig = require("./phishingBlocklist.json");
|
||||
const { storageLocal } = require("./browserApi");
|
||||
const vendored = require("./phishingBlocklist.json");
|
||||
const { HASH_ALGORITHM, HASH_HEX_CHARS, hashDomain } = require("./domainHash");
|
||||
|
||||
const BLOCKLIST_URL =
|
||||
"https://raw.githubusercontent.com/MetaMask/eth-phishing-detect/main/src/config.json";
|
||||
|
||||
const CACHE_TTL_MS = 24 * 60 * 60 * 1000; // 24 hours
|
||||
|
||||
// Floor on how often an unscheduled path may hit the network. The worker is
|
||||
// revived every ~30 seconds while the browser is busy, and every revival runs
|
||||
// the startup path; without a persisted record of the last attempt, any state
|
||||
// that leaves lastFetchTime unset — a fetch that failed, or a delta too large
|
||||
// to store — would download the full list on every single wake.
|
||||
const MIN_FETCH_ATTEMPT_INTERVAL_MS = 60 * 60 * 1000; // 1 hour
|
||||
|
||||
const DELTA_STORAGE_KEY = "phishing-delta";
|
||||
const MAX_DELTA_BYTES = 256 * 1024; // 256 KiB
|
||||
|
||||
// Vendored set — built once from the bundled JSON.
|
||||
const vendoredBlacklist = new Set(
|
||||
(vendoredConfig.blacklist || []).map((d) => d.toLowerCase()),
|
||||
);
|
||||
|
||||
// Delta set — only entries from live list that are NOT in vendored.
|
||||
let deltaBlacklist = new Set();
|
||||
let lastFetchTime = 0;
|
||||
let lastAttemptTime = 0;
|
||||
let fetchPromise = null;
|
||||
let loadPromise = null;
|
||||
|
||||
// storageLocal() resolves on use rather than at module load, so a test can
|
||||
// install a stub after requiring this module, and it returns null where the
|
||||
// API is absent — which is why the popup, with no reason to touch the delta,
|
||||
// loads fine without it.
|
||||
|
||||
/**
|
||||
* Sanitise a timestamp read back from storage.
|
||||
*
|
||||
* A value in the future is permanent poison: every guard here measures elapsed
|
||||
* time as `Date.now() - stamp` and tests only the lower bound, so a stamp a
|
||||
* year ahead suppresses updates for a year with no path that ever clears it.
|
||||
* Clock skew and a restored profile backup both produce one. Since these
|
||||
* timestamps only ever gate work, discarding an impossible one is safe: it
|
||||
* costs at most a single extra fetch and restores a sane value immediately.
|
||||
*
|
||||
* @param {unknown} value
|
||||
* @returns {number} the timestamp, or 0 if it is unusable.
|
||||
*/
|
||||
function sanitizeTimestamp(value) {
|
||||
if (typeof value !== "number" || !Number.isFinite(value)) return 0;
|
||||
if (value <= 0 || value > Date.now()) return 0;
|
||||
return value;
|
||||
}
|
||||
|
||||
/**
|
||||
* Load the persisted delta and its timestamps from extension storage.
|
||||
* Runs once per worker lifetime; every entry point funnels through
|
||||
* ensureDeltaLoaded() so a wake from termination restores state exactly once.
|
||||
*
|
||||
* @returns {Promise<void>}
|
||||
*/
|
||||
async function loadDeltaFromStorage() {
|
||||
const storage = storageLocal();
|
||||
if (!storage) return;
|
||||
try {
|
||||
const result = await storage.get(DELTA_STORAGE_KEY);
|
||||
const data = result && result[DELTA_STORAGE_KEY];
|
||||
if (!data) return;
|
||||
if (Array.isArray(data.blacklist)) {
|
||||
deltaBlacklist = new Set(
|
||||
data.blacklist.map((d) => d.toLowerCase()),
|
||||
);
|
||||
}
|
||||
lastFetchTime = sanitizeTimestamp(data.lastFetchTime);
|
||||
lastAttemptTime = sanitizeTimestamp(data.lastAttemptTime);
|
||||
} catch {
|
||||
// Storage unavailable or corrupt — start empty and re-fetch.
|
||||
}
|
||||
}
|
||||
|
||||
function ensureDeltaLoaded() {
|
||||
if (!loadPromise) loadPromise = loadDeltaFromStorage();
|
||||
return loadPromise;
|
||||
}
|
||||
|
||||
/**
|
||||
* Persist the delta and its timestamps if they fit within MAX_DELTA_BYTES.
|
||||
*
|
||||
* The 256 KiB cap covers the delta and its freshness claim: when the delta is
|
||||
* too large to keep, lastFetchTime goes with it, so the next start re-fetches
|
||||
* rather than trusting a freshness claim for a delta it no longer holds.
|
||||
* lastAttemptTime is written either way — it records that the network was
|
||||
* contacted, which stays true whatever became of the response, and it is what
|
||||
* stops a permanently oversized list from downloading on every worker wake.
|
||||
*
|
||||
* @returns {Promise<void>}
|
||||
*/
|
||||
async function saveDeltaToStorage() {
|
||||
const storage = storageLocal();
|
||||
if (!storage) return;
|
||||
try {
|
||||
const data = {
|
||||
blacklist: Array.from(deltaBlacklist),
|
||||
lastFetchTime,
|
||||
lastAttemptTime,
|
||||
};
|
||||
const json = JSON.stringify(data);
|
||||
if (json.length < MAX_DELTA_BYTES) {
|
||||
await storage.set({ [DELTA_STORAGE_KEY]: data });
|
||||
} else if (lastAttemptTime > 0) {
|
||||
await storage.set({ [DELTA_STORAGE_KEY]: { lastAttemptTime } });
|
||||
} else {
|
||||
await storage.remove(DELTA_STORAGE_KEY);
|
||||
}
|
||||
} catch {
|
||||
// Storage unavailable — skip silently
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Load a pre-parsed config and compute the delta against the vendored list.
|
||||
* Used for both live fetches and testing.
|
||||
*
|
||||
* @param {{ blacklist?: string[] }} config
|
||||
* @returns {Promise<void>} resolves once the delta has been persisted.
|
||||
*/
|
||||
function loadConfig(config) {
|
||||
const liveBlacklist = (config.blacklist || []).map((d) => d.toLowerCase());
|
||||
|
||||
// Delta = entries in the live list that are NOT in the vendored list
|
||||
deltaBlacklist = new Set(
|
||||
liveBlacklist.filter((d) => !vendoredBlacklist.has(d)),
|
||||
// The artifact is generated, so a shape it does not have is a build fault, not
|
||||
// a runtime condition. It is checked anyway, and loudly, because every way of
|
||||
// getting it wrong — a stale format, a truncated file, a different digest —
|
||||
// produces a blocklist that matches nothing at all while looking perfectly
|
||||
// healthy. A phishing check that silently answers "no" to everything is the one
|
||||
// failure this module must not have.
|
||||
function checkArtifact(a) {
|
||||
const bad = (why) =>
|
||||
new Error(
|
||||
"phishingBlocklist.json " +
|
||||
why +
|
||||
". It is generated by script/vendor-blocklist; re-run that " +
|
||||
"rather than editing it.",
|
||||
);
|
||||
|
||||
lastFetchTime = Date.now();
|
||||
return saveDeltaToStorage();
|
||||
if (!a || typeof a !== "object") throw bad("is not an object");
|
||||
if (a.algorithm !== HASH_ALGORITHM) {
|
||||
throw bad(
|
||||
"declares algorithm " +
|
||||
JSON.stringify(a.algorithm) +
|
||||
", but this build hashes with " +
|
||||
HASH_ALGORITHM,
|
||||
);
|
||||
}
|
||||
if (a.hashHexChars !== HASH_HEX_CHARS) {
|
||||
throw bad(
|
||||
"declares " +
|
||||
JSON.stringify(a.hashHexChars) +
|
||||
" hex characters per entry, but this build produces " +
|
||||
HASH_HEX_CHARS,
|
||||
);
|
||||
}
|
||||
if (typeof a.hashes !== "string") throw bad("has no hashes string");
|
||||
if (!Number.isInteger(a.count) || a.count < 1) {
|
||||
throw bad("declares no usable entry count");
|
||||
}
|
||||
if (a.hashes.length !== a.count * HASH_HEX_CHARS) {
|
||||
throw bad(
|
||||
"holds " +
|
||||
a.hashes.length +
|
||||
" hex characters, which is not the " +
|
||||
a.count * HASH_HEX_CHARS +
|
||||
" its count of " +
|
||||
a.count +
|
||||
" entries requires",
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
checkArtifact(vendored);
|
||||
|
||||
const HASHES = vendored.hashes;
|
||||
const COUNT = vendored.count;
|
||||
|
||||
/**
|
||||
* Is this digest one of the vendored entries?
|
||||
*
|
||||
* Binary search over fixed-width records. The digests are lowercase hex of one
|
||||
* width, so lexicographic order is numeric order and the artifact is written
|
||||
* sorted; tests assert that ordering against the committed file, because an
|
||||
* unsorted artifact would fail lookups silently rather than loudly.
|
||||
*
|
||||
* @param {string} hash
|
||||
* @returns {boolean}
|
||||
*/
|
||||
function hashListed(hash) {
|
||||
let lo = 0;
|
||||
let hi = COUNT - 1;
|
||||
while (lo <= hi) {
|
||||
const mid = (lo + hi) >> 1;
|
||||
const at = HASHES.slice(
|
||||
mid * HASH_HEX_CHARS,
|
||||
(mid + 1) * HASH_HEX_CHARS,
|
||||
);
|
||||
if (at === hash) return true;
|
||||
if (at < hash) lo = mid + 1;
|
||||
else hi = mid - 1;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -175,161 +126,33 @@ function hostnameVariants(hostname) {
|
||||
|
||||
/**
|
||||
* Check if a hostname is on the phishing blocklist.
|
||||
* Checks delta first (fresh/recent scam sites), then vendored list.
|
||||
*
|
||||
* Synchronous by design — callers answer an approval prompt with it. On a
|
||||
* worker that has just woken, the persisted delta may still be loading; the
|
||||
* vendored list, which is bundled and always present, carries the check until
|
||||
* it lands.
|
||||
*
|
||||
* @param {string} hostname - The hostname to check.
|
||||
* @returns {boolean}
|
||||
*/
|
||||
function isPhishingDomain(hostname) {
|
||||
if (!hostname) return false;
|
||||
const variants = hostnameVariants(hostname);
|
||||
|
||||
// Check delta blacklist first (fresh/recent scam sites), then vendored
|
||||
for (const v of variants) {
|
||||
if (deltaBlacklist.has(v) || vendoredBlacklist.has(v)) return true;
|
||||
for (const variant of hostnameVariants(hostname)) {
|
||||
if (hashListed(hashDomain(variant))) return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* Fetch the latest blocklist and compute delta against vendored data.
|
||||
* De-duplicates concurrent fetches. Results are cached for CACHE_TTL_MS,
|
||||
* counted from the persisted timestamp so the cache outlives the worker.
|
||||
*
|
||||
* `force` is what makes the 24-hour alarm actually refresh every 24 hours.
|
||||
* The alarm fires one period after the previous alarm, but lastFetchTime is
|
||||
* stamped when that fetch *completed*, so an unforced tick lands one fetch
|
||||
* latency inside its own TTL, skips, and turns the real cadence into 48 hours.
|
||||
* Shortening the TTL instead would not fix it: the worker wakes every ~30
|
||||
* seconds and the startup path re-checks the TTL each time, so a shortened TTL
|
||||
* simply becomes the real cadence. The TTL is there to stop redundant fetches
|
||||
* on wake, and the scheduled tick is not redundant, so it bypasses it.
|
||||
*
|
||||
* @param {{force?: boolean}} [opts] force: fetch unless one is already in
|
||||
* flight, ignoring both the freshness and the retry guard. For the scheduled
|
||||
* alarm tick only.
|
||||
* @returns {Promise<void>}
|
||||
*/
|
||||
async function updatePhishingList({ force = false } = {}) {
|
||||
// A worker that has just been revived knows nothing until the persisted
|
||||
// record is back in memory; without this the freshness check below would
|
||||
// always see 0 and re-fetch on every wake.
|
||||
await ensureDeltaLoaded();
|
||||
|
||||
if (!force) {
|
||||
const now = Date.now();
|
||||
// Skip if recently fetched.
|
||||
if (lastFetchTime > 0 && now - lastFetchTime < CACHE_TTL_MS) return;
|
||||
// Skip if the network was contacted recently and the result was not
|
||||
// usable — a failed fetch or an oversized delta leaves lastFetchTime
|
||||
// unset, and without this every wake would retry.
|
||||
if (
|
||||
lastAttemptTime > 0 &&
|
||||
now - lastAttemptTime < MIN_FETCH_ATTEMPT_INTERVAL_MS
|
||||
) {
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
// De-duplicate concurrent calls
|
||||
if (fetchPromise) return fetchPromise;
|
||||
|
||||
fetchPromise = (async () => {
|
||||
lastAttemptTime = Date.now();
|
||||
try {
|
||||
const resp = await fetch(BLOCKLIST_URL);
|
||||
if (!resp.ok) throw new Error("HTTP " + resp.status);
|
||||
const config = await resp.json();
|
||||
await loadConfig(config);
|
||||
} catch {
|
||||
// Silently fail — vendored list still provides coverage. Persist
|
||||
// the attempt so a persistently failing fetch is retried on the
|
||||
// schedule rather than on every wake.
|
||||
await saveDeltaToStorage();
|
||||
} finally {
|
||||
fetchPromise = null;
|
||||
}
|
||||
})();
|
||||
|
||||
return fetchPromise;
|
||||
}
|
||||
|
||||
/**
|
||||
* Restore persisted state and fetch if the list is overdue.
|
||||
*
|
||||
* Called from the background script every time it starts — a fresh install,
|
||||
* a browser start, and every revival of a terminated service worker all land
|
||||
* here. The recurring 24-hour schedule itself is an alarm (see
|
||||
* shared/alarms.js), not a timer, because timers die with the worker.
|
||||
*
|
||||
* @returns {Promise<void>}
|
||||
*/
|
||||
async function initPhishingList() {
|
||||
await ensureDeltaLoaded();
|
||||
return updatePhishingList();
|
||||
}
|
||||
|
||||
/**
|
||||
* The 24-hour alarm tick. Separate from initPhishingList() because this is the
|
||||
* scheduled refresh and must not be vetoed by the guards that exist to keep
|
||||
* the unscheduled startup path off the network.
|
||||
*
|
||||
* @returns {Promise<void>}
|
||||
*/
|
||||
async function refreshPhishingListOnSchedule() {
|
||||
return updatePhishingList({ force: true });
|
||||
}
|
||||
|
||||
/**
|
||||
* Return the total blocklist size (vendored + delta) for diagnostics.
|
||||
* Return the blocklist size for diagnostics.
|
||||
*
|
||||
* @returns {number}
|
||||
*/
|
||||
function getBlocklistSize() {
|
||||
return vendoredBlacklist.size + deltaBlacklist.size;
|
||||
}
|
||||
|
||||
/**
|
||||
* Return the delta blocklist size for diagnostics.
|
||||
*
|
||||
* @returns {number}
|
||||
*/
|
||||
function getDeltaSize() {
|
||||
return deltaBlacklist.size;
|
||||
}
|
||||
|
||||
/**
|
||||
* Reset internal state (for testing).
|
||||
*/
|
||||
function _reset() {
|
||||
deltaBlacklist = new Set();
|
||||
lastFetchTime = 0;
|
||||
lastAttemptTime = 0;
|
||||
fetchPromise = null;
|
||||
loadPromise = null;
|
||||
return COUNT;
|
||||
}
|
||||
|
||||
module.exports = {
|
||||
isPhishingDomain,
|
||||
updatePhishingList,
|
||||
refreshPhishingListOnSchedule,
|
||||
initPhishingList,
|
||||
loadDeltaFromStorage,
|
||||
loadConfig,
|
||||
CACHE_TTL_MS,
|
||||
MIN_FETCH_ATTEMPT_INTERVAL_MS,
|
||||
DELTA_STORAGE_KEY,
|
||||
MAX_DELTA_BYTES,
|
||||
getBlocklistSize,
|
||||
getDeltaSize,
|
||||
hostnameVariants,
|
||||
_reset,
|
||||
// Exposed for testing only
|
||||
_getVendoredBlacklistSize: () => vendoredBlacklist.size,
|
||||
_getDeltaBlacklist: () => deltaBlacklist,
|
||||
// Exposed for testing only: the ends of the search range are where an
|
||||
// off-by-one hides, and reaching them through isPhishingDomain() would mean
|
||||
// knowing which domain hashes to the first or last entry.
|
||||
_hashListed: hashListed,
|
||||
};
|
||||
|
||||
@@ -80,17 +80,12 @@ describe("alarms module", () => {
|
||||
delete global.chrome;
|
||||
});
|
||||
|
||||
test("ensureRecurringAlarms schedules both recurring jobs", async () => {
|
||||
test("ensureRecurringAlarms schedules the recurring job", async () => {
|
||||
const created = await alarmsMod.ensureRecurringAlarms();
|
||||
expect(created).toEqual({ balance: true, phishing: true });
|
||||
expect(created).toEqual({ balance: true, cleared: [] });
|
||||
|
||||
const names = alarmsStub.created.map((c) => c.name).sort();
|
||||
expect(names).toEqual(
|
||||
[
|
||||
alarmsMod.BALANCE_REFRESH_ALARM,
|
||||
alarmsMod.PHISHING_REFRESH_ALARM,
|
||||
].sort(),
|
||||
);
|
||||
const names = alarmsStub.created.map((c) => c.name);
|
||||
expect(names).toEqual([alarmsMod.BALANCE_REFRESH_ALARM]);
|
||||
});
|
||||
|
||||
test("the balance refresh keeps its 60-second cadence", async () => {
|
||||
@@ -99,12 +94,35 @@ describe("alarms module", () => {
|
||||
expect(balance.periodInMinutes).toBe(1);
|
||||
});
|
||||
|
||||
test("the phishing refresh keeps its 24-hour cadence", async () => {
|
||||
test("a retired job's alarm is cleared, not left running", async () => {
|
||||
// The browser holds an alarm until something clears it. Deleting the
|
||||
// job from the code is not enough: on every install that ever ran the
|
||||
// version which created it, the alarm goes on waking the service
|
||||
// worker on its old schedule with nothing to deliver it to.
|
||||
for (const name of alarmsMod.OBSOLETE_ALARMS) {
|
||||
alarmsStub.create(name, { periodInMinutes: 24 * 60 });
|
||||
}
|
||||
expect(alarmsMod.OBSOLETE_ALARMS.length).toBeGreaterThan(0);
|
||||
|
||||
const result = await alarmsMod.ensureRecurringAlarms();
|
||||
expect(result.cleared).toEqual(alarmsMod.OBSOLETE_ALARMS);
|
||||
for (const name of alarmsMod.OBSOLETE_ALARMS) {
|
||||
expect(alarmsStub.alarms.get(name)).toBeUndefined();
|
||||
}
|
||||
});
|
||||
|
||||
test("clearing a retired alarm is not re-reported once it is gone", async () => {
|
||||
await alarmsMod.ensureRecurringAlarms();
|
||||
const phishing = alarmsStub.alarms.get(
|
||||
alarmsMod.PHISHING_REFRESH_ALARM,
|
||||
const again = await alarmsMod.ensureRecurringAlarms();
|
||||
expect(again.cleared).toEqual([]);
|
||||
});
|
||||
|
||||
test("no retired name is also a live one", async () => {
|
||||
// A name in both lists would be created and then cleared on every
|
||||
// start, so the job it schedules would never fire.
|
||||
expect(alarmsMod.OBSOLETE_ALARMS).not.toContain(
|
||||
alarmsMod.BALANCE_REFRESH_ALARM,
|
||||
);
|
||||
expect(phishing.periodInMinutes).toBe(24 * 60);
|
||||
});
|
||||
|
||||
test("no period is below the browser-enforced minimum", async () => {
|
||||
@@ -122,14 +140,14 @@ describe("alarms module", () => {
|
||||
|
||||
test("a revived worker does not reset an existing alarm's schedule", async () => {
|
||||
await alarmsMod.ensureRecurringAlarms();
|
||||
expect(alarmsStub.create).toHaveBeenCalledTimes(2);
|
||||
expect(alarmsStub.create).toHaveBeenCalledTimes(1);
|
||||
|
||||
// Every wake re-runs the startup path. Re-creating an alarm restarts
|
||||
// its period, so a busy extension would push the next fire out
|
||||
// forever and the job would never run.
|
||||
const again = await alarmsMod.ensureRecurringAlarms();
|
||||
expect(again).toEqual({ balance: false, phishing: false });
|
||||
expect(alarmsStub.create).toHaveBeenCalledTimes(2);
|
||||
expect(again).toEqual({ balance: false, cleared: [] });
|
||||
expect(alarmsStub.create).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
test("a missing alarm is re-created on the next start", async () => {
|
||||
@@ -137,7 +155,7 @@ describe("alarms module", () => {
|
||||
await alarmsStub.clear(alarmsMod.BALANCE_REFRESH_ALARM);
|
||||
|
||||
const again = await alarmsMod.ensureRecurringAlarms();
|
||||
expect(again).toEqual({ balance: true, phishing: false });
|
||||
expect(again).toEqual({ balance: true, cleared: [] });
|
||||
expect(
|
||||
alarmsStub.alarms.get(alarmsMod.BALANCE_REFRESH_ALARM),
|
||||
).toBeDefined();
|
||||
@@ -147,17 +165,17 @@ describe("alarms module", () => {
|
||||
// An install carries its alarms across an extension update, so a
|
||||
// period changed in a new release only ever reaches users if the
|
||||
// stale one is reconciled.
|
||||
alarmsStub.create(alarmsMod.PHISHING_REFRESH_ALARM, {
|
||||
alarmsStub.create(alarmsMod.BALANCE_REFRESH_ALARM, {
|
||||
periodInMinutes: 7 * 24 * 60,
|
||||
});
|
||||
alarmsStub.create.mockClear();
|
||||
|
||||
const created = await alarmsMod.ensureRecurringAlarms();
|
||||
expect(created.phishing).toBe(true);
|
||||
expect(created.balance).toBe(true);
|
||||
expect(
|
||||
alarmsStub.alarms.get(alarmsMod.PHISHING_REFRESH_ALARM)
|
||||
alarmsStub.alarms.get(alarmsMod.BALANCE_REFRESH_ALARM)
|
||||
.periodInMinutes,
|
||||
).toBe(alarmsMod.PHISHING_REFRESH_PERIOD_MINUTES);
|
||||
).toBe(alarmsMod.BALANCE_REFRESH_PERIOD_MINUTES);
|
||||
});
|
||||
|
||||
test("reconciling a period settles instead of re-creating forever", async () => {
|
||||
@@ -168,31 +186,31 @@ describe("alarms module", () => {
|
||||
alarmsStub.create.mockClear();
|
||||
|
||||
const again = await alarmsMod.ensureRecurringAlarms();
|
||||
expect(again).toEqual({ balance: false, phishing: false });
|
||||
expect(again).toEqual({ balance: false, cleared: [] });
|
||||
expect(alarmsStub.create).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
test("handlers are dispatched by alarm name from one listener", () => {
|
||||
const balance = jest.fn();
|
||||
const phishing = jest.fn();
|
||||
const other = jest.fn();
|
||||
expect(
|
||||
alarmsMod.registerAlarmHandlers({
|
||||
[alarmsMod.BALANCE_REFRESH_ALARM]: balance,
|
||||
[alarmsMod.PHISHING_REFRESH_ALARM]: phishing,
|
||||
"autistmask-some-other-job": other,
|
||||
}),
|
||||
).toBe(true);
|
||||
expect(alarmsStub.listenerCount()).toBe(1);
|
||||
|
||||
alarmsStub.fire(alarmsMod.BALANCE_REFRESH_ALARM);
|
||||
expect(balance).toHaveBeenCalledTimes(1);
|
||||
expect(phishing).not.toHaveBeenCalled();
|
||||
expect(other).not.toHaveBeenCalled();
|
||||
|
||||
alarmsStub.fire(alarmsMod.PHISHING_REFRESH_ALARM);
|
||||
expect(phishing).toHaveBeenCalledTimes(1);
|
||||
alarmsStub.fire("autistmask-some-other-job");
|
||||
expect(other).toHaveBeenCalledTimes(1);
|
||||
|
||||
alarmsStub.fire("some-other-extension-alarm");
|
||||
alarmsStub.fire("an-alarm-with-no-handler");
|
||||
expect(balance).toHaveBeenCalledTimes(1);
|
||||
expect(phishing).toHaveBeenCalledTimes(1);
|
||||
expect(other).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
test("Firefox MV2 gets the same treatment via browser.alarms", async () => {
|
||||
@@ -205,8 +223,8 @@ describe("alarms module", () => {
|
||||
try {
|
||||
const mod = require("../src/shared/alarms");
|
||||
const created = await mod.ensureRecurringAlarms();
|
||||
expect(created).toEqual({ balance: true, phishing: true });
|
||||
expect(firefoxAlarms.created).toHaveLength(2);
|
||||
expect(created).toEqual({ balance: true, cleared: [] });
|
||||
expect(firefoxAlarms.created).toHaveLength(1);
|
||||
// The Chrome stub must not have been touched.
|
||||
expect(alarmsStub.create).not.toHaveBeenCalled();
|
||||
} finally {
|
||||
@@ -220,7 +238,7 @@ describe("alarms module", () => {
|
||||
const mod = require("../src/shared/alarms");
|
||||
await expect(mod.ensureRecurringAlarms()).resolves.toEqual({
|
||||
balance: false,
|
||||
phishing: false,
|
||||
cleared: [],
|
||||
});
|
||||
expect(mod.registerAlarmHandlers({})).toBe(false);
|
||||
});
|
||||
@@ -274,9 +292,12 @@ function loadBackground(initialStore = {}) {
|
||||
tabs: { query: jest.fn(), sendMessage: jest.fn() },
|
||||
action: { setPopup: jest.fn() },
|
||||
};
|
||||
// Present so that a startup path which went to the network would be
|
||||
// recorded rather than throwing, which is what makes "no request was made"
|
||||
// an observation instead of an assumption.
|
||||
global.fetch = jest.fn(async () => ({
|
||||
ok: true,
|
||||
json: async () => ({ blacklist: [] }),
|
||||
json: async () => ({}),
|
||||
}));
|
||||
jest.resetModules();
|
||||
require("../src/background/index");
|
||||
@@ -318,17 +339,21 @@ describe("background worker scheduling", () => {
|
||||
// Let the startup path's promises settle.
|
||||
await settle();
|
||||
|
||||
const names = alarmsStub.created.map((c) => c.name).sort();
|
||||
const {
|
||||
BALANCE_REFRESH_ALARM,
|
||||
PHISHING_REFRESH_ALARM,
|
||||
} = require("../src/shared/alarms");
|
||||
expect(names).toEqual(
|
||||
[BALANCE_REFRESH_ALARM, PHISHING_REFRESH_ALARM].sort(),
|
||||
);
|
||||
const names = alarmsStub.created.map((c) => c.name);
|
||||
const { BALANCE_REFRESH_ALARM } = require("../src/shared/alarms");
|
||||
expect(names).toEqual([BALANCE_REFRESH_ALARM]);
|
||||
expect(mockSetIntervalCalls).toBe(0);
|
||||
});
|
||||
|
||||
test("startup contacts nothing", async () => {
|
||||
// The phishing blocklist is vendored at build time and there is no
|
||||
// other startup fetch, so a worker coming up asks nobody anything.
|
||||
// Every wake used to be a candidate for a blocklist download.
|
||||
loadBackground();
|
||||
await settle();
|
||||
expect(global.fetch).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
test("an onAlarm listener is installed on startup", async () => {
|
||||
alarmsStub = loadBackground().alarmsStub;
|
||||
await settle();
|
||||
@@ -348,7 +373,7 @@ describe("background worker scheduling", () => {
|
||||
alarmsStub.created.length = 0;
|
||||
loaded.listeners.onStartup[0]();
|
||||
await settle();
|
||||
expect(alarmsStub.created).toHaveLength(2);
|
||||
expect(alarmsStub.created).toHaveLength(1);
|
||||
});
|
||||
|
||||
test("the install-time listener and the top-level call share one run", async () => {
|
||||
@@ -360,13 +385,10 @@ describe("background worker scheduling", () => {
|
||||
loaded.listeners.onInstalled[0]();
|
||||
await settle();
|
||||
|
||||
expect(alarmsStub.created).toHaveLength(2);
|
||||
expect(alarmsStub.created.map((c) => c.name).sort()).toEqual(
|
||||
[
|
||||
expect(alarmsStub.created).toHaveLength(1);
|
||||
expect(alarmsStub.created.map((c) => c.name)).toEqual([
|
||||
"autistmask-balance-refresh",
|
||||
"autistmask-phishing-refresh",
|
||||
].sort(),
|
||||
);
|
||||
]);
|
||||
});
|
||||
});
|
||||
|
||||
|
||||
@@ -157,12 +157,9 @@ function loadBackground(options) {
|
||||
}));
|
||||
jest.doMock("../src/shared/phishingDomains", () => ({
|
||||
isPhishingDomain: () => false,
|
||||
refreshPhishingListOnSchedule: jest.fn(async () => {}),
|
||||
initPhishingList: jest.fn(async () => {}),
|
||||
}));
|
||||
jest.doMock("../src/shared/alarms", () => ({
|
||||
BALANCE_REFRESH_ALARM: "balance",
|
||||
PHISHING_REFRESH_ALARM: "phishing",
|
||||
BALANCE_REFRESH_PERIOD_MINUTES: 1,
|
||||
ensureRecurringAlarms: jest.fn(async () => {}),
|
||||
registerAlarmHandlers: jest.fn(),
|
||||
|
||||
@@ -13,7 +13,7 @@ const os = require("os");
|
||||
const path = require("path");
|
||||
|
||||
const { chromium } = require("playwright-core");
|
||||
const { installNetworkStubs } = require("./network");
|
||||
const { installNetworkStubs, WORKER_PROBE_URL } = require("./network");
|
||||
|
||||
const REPO_ROOT = path.resolve(__dirname, "..", "..");
|
||||
const EXT_PATH = path.join(REPO_ROOT, "dist", "chrome");
|
||||
@@ -129,42 +129,109 @@ function attachErrorListeners(ctx, errors) {
|
||||
// if it ever stops being.
|
||||
}
|
||||
|
||||
function sleep(ms) {
|
||||
return new Promise((resolve) => setTimeout(resolve, ms));
|
||||
}
|
||||
|
||||
// The most recently seen background worker, waiting for one if none has
|
||||
// appeared yet. Most recent rather than first: Chrome stops an idle MV3
|
||||
// worker and starts a fresh one on the next event, and a handle to a
|
||||
// stopped worker cannot be evaluated in.
|
||||
async function serviceWorker(ctx) {
|
||||
const [existing] = ctx.serviceWorkers();
|
||||
if (existing) return existing;
|
||||
const workers = ctx.serviceWorkers();
|
||||
const latest = workers[workers.length - 1];
|
||||
if (latest) return latest;
|
||||
return ctx.waitForEvent("serviceworker", { timeout: 30000 });
|
||||
}
|
||||
|
||||
// How long to wait for the background worker's first outbound request.
|
||||
//
|
||||
// The margin that actually decides whether this check is sound is not
|
||||
// this timeout — it is whether the route handler is installed before the
|
||||
// worker fetches. Measured over several runs: route installation
|
||||
// completes 11-23ms after the context comes up, and the worker's
|
||||
// blocklist fetch arrives 525-883ms after that, so the route wins by
|
||||
// roughly 25-50x. This 30s figure is only slack for a loaded machine on
|
||||
// top of that; losing the race fails the run rather than passing it
|
||||
// quietly, which was verified by forcing a 3s delay before route
|
||||
// installation.
|
||||
// How long to wait for the probe request the worker is asked to make.
|
||||
const WORKER_TRAFFIC_TIMEOUT_MS = 30000;
|
||||
|
||||
// ctx.route() only sees service-worker requests when Playwright runs with
|
||||
// PW_EXPERIMENTAL_SERVICE_WORKER_NETWORK_EVENTS=1, which script/test-e2e
|
||||
// sets. Without it the worker's traffic — notably the phishing blocklist
|
||||
// fetch src/background/index.js issues at startup — goes to the real
|
||||
// internet, and nothing says so, because src/shared/phishingDomains.js
|
||||
// swallows fetch failures. A harness whose isolation can lapse in silence
|
||||
// is worthless, so this does not take the flag on trust: the background
|
||||
// worker's own startup fetch has to show up in the route handler, or the
|
||||
// suite refuses to run.
|
||||
// sets. Without it every fetch the background worker makes goes to the
|
||||
// real internet and nothing says so. A harness whose isolation can lapse
|
||||
// in silence is worthless, so this does not take the flag on trust: a
|
||||
// request the worker itself issues has to show up in the route handler,
|
||||
// or the suite refuses to run.
|
||||
//
|
||||
// Deliberately NOT a synthetic probe fetched through worker.evaluate():
|
||||
// evaluating in an extension worker this early kills it (the call fails
|
||||
// with "Target page, context or browser has been closed" and the worker
|
||||
// disappears), which would break the very thing being measured. Observing
|
||||
// traffic the extension already generates costs nothing and cannot
|
||||
// perturb it.
|
||||
async function assertWorkerTrafficIntercepted(stubs) {
|
||||
// The anchor is a probe the harness asks the worker for, not traffic the
|
||||
// extension generates on its own. It used to be the phishing blocklist
|
||||
// fetch src/background/index.js issued at startup; that fetch is gone —
|
||||
// the blocklist is vendored at build time and the extension contacts
|
||||
// nobody when it starts — so there is no longer any startup traffic to
|
||||
// observe and the check generates its own.
|
||||
//
|
||||
// Evaluating in the worker straight after launch does not work, and that
|
||||
// is not a stale observation: it was tried again here and failed with
|
||||
// "Target page, context or browser has been closed" on the first run.
|
||||
// Chrome stops the freshly registered worker as soon as it has nothing to
|
||||
// do, and the extension no longer gives it anything to do — which is the
|
||||
// same change that removed the old anchor. So the probe wakes the worker
|
||||
// before it evaluates in it, by sending it a message from an extension
|
||||
// page and waiting for the reply: delivering a message is what starts a
|
||||
// stopped worker, and a worker that has just answered one is alive.
|
||||
// The evaluated fetch is not awaited, so nothing in the worker is held
|
||||
// open by the probe either.
|
||||
async function wakeWorker(ctx) {
|
||||
const sw = await serviceWorker(ctx);
|
||||
const extensionId = new URL(sw.url()).host;
|
||||
const page = await ctx.newPage();
|
||||
try {
|
||||
await page.goto(
|
||||
"chrome-extension://" + extensionId + "/src/popup/index.html",
|
||||
);
|
||||
// eth_chainId is answered from local state: it wakes the worker
|
||||
// and changes nothing.
|
||||
await page.evaluate(
|
||||
() =>
|
||||
new Promise((resolve) => {
|
||||
chrome.runtime.sendMessage(
|
||||
{
|
||||
type: "AUTISTMASK_RPC",
|
||||
method: "eth_chainId",
|
||||
params: [],
|
||||
},
|
||||
() => resolve(null),
|
||||
);
|
||||
}),
|
||||
);
|
||||
} finally {
|
||||
await page.close();
|
||||
}
|
||||
}
|
||||
|
||||
async function probeFromWorker(ctx, url) {
|
||||
let lastError = null;
|
||||
for (let attempt = 0; attempt < 5; attempt++) {
|
||||
try {
|
||||
await wakeWorker(ctx);
|
||||
const sw = await serviceWorker(ctx);
|
||||
await sw.evaluate((u) => {
|
||||
// Deliberately not awaited and never rejected: what is
|
||||
// being observed is that the request reaches the route
|
||||
// handler, and an unhandled rejection in the worker would
|
||||
// be collected as a suite error if it did not.
|
||||
fetch(u).catch(() => {});
|
||||
}, url);
|
||||
return;
|
||||
} catch (e) {
|
||||
lastError = e;
|
||||
await sleep(500);
|
||||
}
|
||||
}
|
||||
throw new Error(
|
||||
"could not ask the background worker to fetch " +
|
||||
url +
|
||||
", so service-worker interception was never tested. Last " +
|
||||
"error: " +
|
||||
(lastError && lastError.message),
|
||||
);
|
||||
}
|
||||
|
||||
async function assertWorkerTrafficIntercepted(ctx, stubs) {
|
||||
await probeFromWorker(ctx, WORKER_PROBE_URL);
|
||||
|
||||
const seen = await stubs.waitForServiceWorkerTraffic(
|
||||
WORKER_TRAFFIC_TIMEOUT_MS,
|
||||
);
|
||||
@@ -177,19 +244,16 @@ async function assertWorkerTrafficIntercepted(stubs) {
|
||||
throw new Error(
|
||||
"observed no service-worker request in the route handler within " +
|
||||
WORKER_TRAFFIC_TIMEOUT_MS +
|
||||
"ms. Under working interception the background worker's " +
|
||||
"startup blocklist fetch (src/background/index.js) reaches the " +
|
||||
"handler about half a second after the route is installed. " +
|
||||
"Two causes are plausible and this check cannot distinguish " +
|
||||
"ms, although the background worker was asked to fetch " +
|
||||
WORKER_PROBE_URL +
|
||||
". Two causes are plausible and this check cannot distinguish " +
|
||||
"them: (1) service-worker interception is not in effect, so " +
|
||||
"that traffic went to the real internet unobserved — the suite " +
|
||||
"that request went to the real internet unobserved — the suite " +
|
||||
"must be run through script/test-e2e, which sets " +
|
||||
"PW_EXPERIMENTAL_SERVICE_WORKER_NETWORK_EVENTS=1, and a " +
|
||||
"Playwright upgrade may have dropped or renamed that flag; " +
|
||||
"(2) no worker request was made in the first place — the route " +
|
||||
"lost the startup race, or the worker no longer fetches at " +
|
||||
"startup, in which case this check needs a new anchor because " +
|
||||
"there is no longer any worker traffic to observe. Either way " +
|
||||
"(2) the probe never ran, because the worker was torn down " +
|
||||
"between being handed over and being evaluated in. Either way " +
|
||||
"the fix is a replacement mechanism or an honest downgrade of " +
|
||||
"the isolation claims in tests/e2e/network.js and README.md — " +
|
||||
"not deleting this check",
|
||||
@@ -241,7 +305,7 @@ async function launch(routeOpts) {
|
||||
routeOpts.report = (text) => errors.record("network", text);
|
||||
const stubs = await installNetworkStubs(ctx, routeOpts);
|
||||
|
||||
await assertWorkerTrafficIntercepted(stubs);
|
||||
await assertWorkerTrafficIntercepted(ctx, stubs);
|
||||
|
||||
// The extension id is derived from the unpacked path, so it
|
||||
// changes and must never be hardcoded. It is the host part of the
|
||||
|
||||
@@ -9,13 +9,12 @@
|
||||
//
|
||||
// Service-worker coverage is not free: ctx.route() only sees worker
|
||||
// traffic when PW_EXPERIMENTAL_SERVICE_WORKER_NETWORK_EVENTS=1 is set in
|
||||
// the environment, which script/test-e2e does. Without it the phishing
|
||||
// blocklist fetch that src/background/index.js issues at worker startup
|
||||
// silently reaches raw.githubusercontent.com on the open internet, and
|
||||
// src/shared/phishingDomains.js swallows the failure so nothing surfaces
|
||||
// it. That is not left to trust: waitForServiceWorkerTraffic() below
|
||||
// backs the launch-time canary in harness.js, which fails the entire
|
||||
// suite if worker requests stop being visible here.
|
||||
// the environment, which script/test-e2e does. Without it every fetch the
|
||||
// MV3 background worker makes — the JSON-RPC calls behind every approval
|
||||
// in this suite among them — goes to the real internet unobserved. That is
|
||||
// not left to trust: waitForServiceWorkerTraffic() below backs the
|
||||
// launch-time canary in harness.js, which fails the entire suite if worker
|
||||
// requests stop being visible here.
|
||||
//
|
||||
// Anything not explicitly stubbed here is aborted AND reported to the
|
||||
// error collector, so a newly added outbound call shows up as a test
|
||||
@@ -103,6 +102,22 @@ function word(value) {
|
||||
const DAPP_ORIGIN = "https://dapp.e2e.test";
|
||||
const DAPP_URL = DAPP_ORIGIN + "/";
|
||||
|
||||
// The same page, served from a hostname that is on the vendored phishing
|
||||
// blocklist, so the phishing warning can be driven end to end against the real
|
||||
// list rather than a stub of it. It is a live entry at the pinned upstream
|
||||
// commit; upstream prunes, so a re-vendoring run that retires it turns the
|
||||
// phishing test red, and the fix is a current entry, not a weaker assertion.
|
||||
const PHISHING_DAPP_ORIGIN = "https://myetheywallet.com";
|
||||
const PHISHING_DAPP_URL = PHISHING_DAPP_ORIGIN + "/";
|
||||
|
||||
// A request the harness asks the background service worker to make, purely so
|
||||
// that worker interception can be proved before any test runs. Nothing in the
|
||||
// extension fetches at startup any more — the blocklist is vendored at build
|
||||
// time — so the canary in harness.js has no product traffic to anchor on and
|
||||
// generates its own. See assertWorkerTrafficIntercepted().
|
||||
const WORKER_PROBE_ORIGIN = "https://worker-probe.e2e.test";
|
||||
const WORKER_PROBE_URL = WORKER_PROBE_ORIGIN + "/canary";
|
||||
|
||||
// Requests are parked rather than awaited. An approval prompt only exists
|
||||
// while its call is in flight, so a test that awaited the promise could
|
||||
// never drive the popup that has to settle it; start() files the promise
|
||||
@@ -555,10 +570,9 @@ async function installNetworkStubs(ctx, opts) {
|
||||
// E2E_TRACE_NETWORK=1 prints every request that reaches this handler,
|
||||
// tagged [sw] when it originated in the background service worker.
|
||||
// It exists so the isolation claim above can be re-checked by anyone
|
||||
// in one command, without editing files: the phishing blocklist fetch
|
||||
// showing up with an [sw] tag is the proof that the worker really is
|
||||
// intercepted and that the raw.githubusercontent.com stub below is
|
||||
// live code rather than decoration.
|
||||
// in one command, without editing files: the canary probe and then
|
||||
// every JSON-RPC call behind an approval showing up with an [sw] tag
|
||||
// is the proof that the worker really is intercepted.
|
||||
const trace = traceEnabled(process.env.E2E_TRACE_NETWORK);
|
||||
|
||||
// Regex rather than a glob so chrome-extension:// resource loads are
|
||||
@@ -589,7 +603,11 @@ async function installNetworkStubs(ctx, opts) {
|
||||
// trips run against a real http(s) origin — which is what makes the
|
||||
// shipped content scripts inject at all — without any remote origin
|
||||
// being involved.
|
||||
if (url.origin === DAPP_ORIGIN && p === "/") {
|
||||
if (
|
||||
(url.origin === DAPP_ORIGIN ||
|
||||
url.origin === PHISHING_DAPP_ORIGIN) &&
|
||||
p === "/"
|
||||
) {
|
||||
return route.fulfill({
|
||||
status: 200,
|
||||
contentType: "text/html; charset=utf-8",
|
||||
@@ -635,18 +653,10 @@ async function installNetworkStubs(ctx, opts) {
|
||||
return jsonResponse(route, { Data: {} });
|
||||
}
|
||||
|
||||
// MetaMask phishing blocklist
|
||||
if (
|
||||
url.hostname === "raw.githubusercontent.com" ||
|
||||
p.endsWith("/eth-phishing-detect/main/src/config.json")
|
||||
) {
|
||||
return jsonResponse(route, {
|
||||
version: 2,
|
||||
tolerance: 2,
|
||||
fuzzylist: [],
|
||||
whitelist: [],
|
||||
blacklist: [],
|
||||
});
|
||||
// The interception canary's own request. Answered with nothing: what
|
||||
// is being observed is that it arrived here at all.
|
||||
if (url.href === WORKER_PROBE_URL) {
|
||||
return route.fulfill({ status: 204, body: "" });
|
||||
}
|
||||
|
||||
// Best-effort Etherscan address labels: served as an empty page.
|
||||
@@ -667,12 +677,12 @@ async function installNetworkStubs(ctx, opts) {
|
||||
* Resolve with the first service-worker-originated request this
|
||||
* handler saw, or null if none arrives within `ms`.
|
||||
*
|
||||
* The background worker fetches the phishing blocklist at
|
||||
* startup, unconditionally, within about a second of the context
|
||||
* coming up — so under working interception this resolves almost
|
||||
* immediately. Nothing arriving means worker traffic is bypassing
|
||||
* the handler entirely and going to the real internet, which the
|
||||
* caller turns into a hard failure of the whole suite.
|
||||
* The caller asks the worker for one request of its own (see
|
||||
* WORKER_PROBE_URL) and then waits here, so under working
|
||||
* interception this resolves almost immediately. Nothing arriving
|
||||
* means worker traffic is bypassing the handler entirely and going
|
||||
* to the real internet, which the caller turns into a hard failure
|
||||
* of the whole suite.
|
||||
*/
|
||||
waitForServiceWorkerTraffic(ms) {
|
||||
if (firstWorkerRequest) return Promise.resolve(firstWorkerRequest);
|
||||
@@ -696,6 +706,9 @@ module.exports = {
|
||||
DAPP_HTML,
|
||||
DAPP_ORIGIN,
|
||||
DAPP_URL,
|
||||
PHISHING_DAPP_ORIGIN,
|
||||
PHISHING_DAPP_URL,
|
||||
WORKER_PROBE_URL,
|
||||
FEE_ESTIMATE_WEI,
|
||||
FEE_RESERVE_WEI,
|
||||
STUB_COUNTERPARTY,
|
||||
|
||||
@@ -33,6 +33,7 @@ const {
|
||||
const {
|
||||
DAPP_ORIGIN,
|
||||
DAPP_URL,
|
||||
PHISHING_DAPP_URL,
|
||||
FEE_ESTIMATE_WEI,
|
||||
FEE_RESERVE_WEI,
|
||||
STUB_COUNTERPARTY,
|
||||
@@ -2069,9 +2070,9 @@ async function extensionActiveAddress(page) {
|
||||
return getAddress(address);
|
||||
}
|
||||
|
||||
async function openDapp(ctx) {
|
||||
async function openDapp(ctx, url = DAPP_URL) {
|
||||
const page = await ctx.newPage();
|
||||
await page.goto(DAPP_URL);
|
||||
await page.goto(url);
|
||||
// window.ethereum is not the fixture's doing — it is the shipped
|
||||
// MAIN-world content script. Waiting for it is waiting for the real
|
||||
// provider to have injected itself into a real http(s) origin.
|
||||
@@ -2543,6 +2544,15 @@ test("eth_requestAccounts rejected at the prompt returns a rejection (#183)", as
|
||||
JSON.stringify(hostname),
|
||||
);
|
||||
|
||||
// The control for the phishing test below: this origin is not on the
|
||||
// blocklist, so the banner must be absent here. Without it a banner
|
||||
// that was simply always visible would satisfy that test.
|
||||
assert(
|
||||
await popup.locator("#approve-site-phishing-warning").isHidden(),
|
||||
"the phishing warning is showing for an origin that is not on " +
|
||||
"the blocklist, so its appearance proves nothing",
|
||||
);
|
||||
|
||||
// Deliberately not remembered: a remembered rejection lands the
|
||||
// origin in deniedSites and every later test in this section is
|
||||
// auto-rejected with no prompt at all, which would look like a pass.
|
||||
@@ -2606,6 +2616,53 @@ test("eth_requestAccounts approved returns the selected address (#183)", async (
|
||||
);
|
||||
});
|
||||
|
||||
test("a connect request from a blocklisted site is flagged (#219)", async (env) => {
|
||||
// The vendored blocklist, end to end: a real entry from the shipped
|
||||
// artifact, served as a real http(s) origin, reaching the real background
|
||||
// check and the real approval screen. Nothing about the list is stubbed —
|
||||
// there is nothing left to stub, since the extension no longer fetches it.
|
||||
const phishingDapp = await openDapp(env.ctx, PHISHING_DAPP_URL);
|
||||
const hostname = new URL(PHISHING_DAPP_URL).hostname;
|
||||
try {
|
||||
await reserveApprovalTab(env);
|
||||
await startRequest(
|
||||
phishingDapp,
|
||||
"phishing-accounts",
|
||||
"eth_requestAccounts",
|
||||
[],
|
||||
);
|
||||
const popup = await openSiteApprovalPopup(env);
|
||||
try {
|
||||
await visible(popup, "#view-approve-site");
|
||||
|
||||
const shown = await popup.locator("#approve-hostname").innerText();
|
||||
assert(
|
||||
shown === hostname,
|
||||
"the site prompt names the wrong origin: " +
|
||||
JSON.stringify(shown),
|
||||
);
|
||||
|
||||
await visible(popup, "#approve-site-phishing-warning");
|
||||
console.log("# phishing warning shown for " + hostname);
|
||||
|
||||
// Not remembered: a remembered decision for this origin would
|
||||
// outlive the test.
|
||||
await popup.uncheck("#approve-remember");
|
||||
await popup.click("#btn-reject");
|
||||
|
||||
await assertUserRejection(
|
||||
phishingDapp,
|
||||
"phishing-accounts",
|
||||
"the blocklisted site's eth_requestAccounts",
|
||||
);
|
||||
} finally {
|
||||
await closeApprovalPages(env.ctx);
|
||||
}
|
||||
} finally {
|
||||
await phishingDapp.close();
|
||||
}
|
||||
});
|
||||
|
||||
test("personal_sign signs, and the signature recovers to the address (#183)", async (env) => {
|
||||
await startRequest(env.dapp, "sign", "personal_sign", [
|
||||
SIGN_HEX,
|
||||
|
||||
@@ -1,93 +1,128 @@
|
||||
// Extension storage stub for the Node test environment. The module resolves
|
||||
// the storage API on use, so this only has to exist before the first call.
|
||||
// Values round-trip through JSON the way structured cloning would, so a test
|
||||
// cannot pass by holding a live reference to the module's own array.
|
||||
const storageStore = {};
|
||||
global.chrome = {
|
||||
storage: {
|
||||
local: {
|
||||
get: async (key) =>
|
||||
Object.prototype.hasOwnProperty.call(storageStore, key)
|
||||
? { [key]: JSON.parse(JSON.stringify(storageStore[key])) }
|
||||
: {},
|
||||
set: async (items) => {
|
||||
for (const [key, value] of Object.entries(items)) {
|
||||
storageStore[key] = JSON.parse(JSON.stringify(value));
|
||||
}
|
||||
},
|
||||
remove: async (key) => {
|
||||
delete storageStore[key];
|
||||
},
|
||||
},
|
||||
},
|
||||
};
|
||||
// The phishing blocklist is vendored at build time and shipped as digests:
|
||||
// script/vendor-blocklist writes src/shared/phishingBlocklist.json, and nothing
|
||||
// fetches anything at runtime. Two things therefore have to be proven here, and
|
||||
// the second is the one that would otherwise fail silently:
|
||||
//
|
||||
// - real domains from the vendored list are detected, and clean ones are not.
|
||||
// - a malformed artifact fails loudly. Every way of getting the artifact
|
||||
// wrong produces a blocklist that matches nothing while looking healthy,
|
||||
// which is a phishing check that answers "no" to everything.
|
||||
|
||||
const {
|
||||
isPhishingDomain,
|
||||
loadConfig,
|
||||
getBlocklistSize,
|
||||
getDeltaSize,
|
||||
hostnameVariants,
|
||||
DELTA_STORAGE_KEY,
|
||||
_reset,
|
||||
_getVendoredBlacklistSize,
|
||||
_getDeltaBlacklist,
|
||||
} = require("../src/shared/phishingDomains");
|
||||
const { HASH_HEX_CHARS, hashDomain } = require("../src/shared/domainHash");
|
||||
const vendored = require("../src/shared/phishingBlocklist.json");
|
||||
|
||||
function clearStorage() {
|
||||
for (const key of Object.keys(storageStore)) {
|
||||
delete storageStore[key];
|
||||
// Domains present in the vendored list at the pinned upstream commit. Upstream
|
||||
// prunes as well as adds, so re-vendoring can retire one of these and turn this
|
||||
// red; that is the intended prompt to pick a current entry, not a licence to
|
||||
// weaken the assertion into "some domain somewhere matches".
|
||||
const LISTED = [
|
||||
"0-google.ph",
|
||||
"myetheywallet.com",
|
||||
// An underscore is not legal in a hostname, but DNS carries one and
|
||||
// browsers resolve it, and upstream lists well over a hundred phishing
|
||||
// sites that use one. The vendoring transform keeps them.
|
||||
"phntum-wallett.godaddysites.com",
|
||||
"coinbase_prologin1.godaddysites.com",
|
||||
];
|
||||
|
||||
// Not on the list, and the kind of host a user actually visits.
|
||||
const CLEAN = ["etherscan.io", "example.com", "opensea.io", "sneak.berlin"];
|
||||
|
||||
describe("vendored blocklist", () => {
|
||||
test("the artifact holds the whole list", () => {
|
||||
expect(getBlocklistSize()).toBeGreaterThan(100000);
|
||||
expect(vendored.hashes).toHaveLength(vendored.count * HASH_HEX_CHARS);
|
||||
});
|
||||
|
||||
test("the digests are sorted and unique", () => {
|
||||
// The lookup is a binary search over the concatenated digests. An
|
||||
// unsorted or duplicated artifact would fail lookups quietly rather
|
||||
// than loudly, so the ordering the search depends on is asserted here
|
||||
// against the committed file rather than assumed of the generator.
|
||||
// One assertion at the end rather than one per entry: 100k+ expect()
|
||||
// calls cost seconds, and make test is capped at 30 for the whole
|
||||
// suite. The index of the first offender is reported, so a failure
|
||||
// still says where.
|
||||
let previous = "";
|
||||
let outOfOrderAt = -1;
|
||||
for (let i = 0; i < vendored.count; i++) {
|
||||
const at = vendored.hashes.slice(
|
||||
i * HASH_HEX_CHARS,
|
||||
(i + 1) * HASH_HEX_CHARS,
|
||||
);
|
||||
if (at <= previous) {
|
||||
outOfOrderAt = i;
|
||||
break;
|
||||
}
|
||||
}
|
||||
previous = at;
|
||||
}
|
||||
expect(outOfOrderAt).toBe(-1);
|
||||
});
|
||||
|
||||
// The MV3 service worker is torn down when idle and re-evaluated on the next
|
||||
// event, which wipes every module-level variable. Re-requiring the module with
|
||||
// the registry reset is exactly that: fresh in-memory state, same extension
|
||||
// storage underneath.
|
||||
function restartWorker() {
|
||||
jest.resetModules();
|
||||
return require("../src/shared/phishingDomains");
|
||||
}
|
||||
test("every digest is lowercase hex of the declared width", () => {
|
||||
expect(vendored.hashes).toMatch(/^[0-9a-f]*$/);
|
||||
});
|
||||
|
||||
// Reset delta state before each test to avoid cross-test contamination.
|
||||
// Note: vendored sets are immutable and always present.
|
||||
beforeEach(() => {
|
||||
_reset();
|
||||
clearStorage();
|
||||
test("detects domains from the vendored list", () => {
|
||||
for (const domain of LISTED) {
|
||||
expect(isPhishingDomain(domain)).toBe(true);
|
||||
}
|
||||
});
|
||||
|
||||
test("does not flag legitimate domains", () => {
|
||||
for (const domain of CLEAN) {
|
||||
expect(isPhishingDomain(domain)).toBe(false);
|
||||
}
|
||||
});
|
||||
|
||||
test("detects a subdomain of a listed domain", () => {
|
||||
expect(isPhishingDomain("wallet." + LISTED[0])).toBe(true);
|
||||
expect(isPhishingDomain("a.b.c." + LISTED[0])).toBe(true);
|
||||
});
|
||||
|
||||
test("matching is case-insensitive", () => {
|
||||
expect(isPhishingDomain(LISTED[0].toUpperCase())).toBe(true);
|
||||
});
|
||||
|
||||
test("returns false for an empty or missing hostname", () => {
|
||||
expect(isPhishingDomain("")).toBe(false);
|
||||
expect(isPhishingDomain(null)).toBe(false);
|
||||
expect(isPhishingDomain(undefined)).toBe(false);
|
||||
});
|
||||
|
||||
test("the first and last entries are both reachable", () => {
|
||||
// The ends are where an off-by-one in a binary search hides: a search
|
||||
// that never examines index 0 or index count-1 still finds everything
|
||||
// in between, and the real list is not searched exhaustively here.
|
||||
const first = vendored.hashes.slice(0, HASH_HEX_CHARS);
|
||||
const last = vendored.hashes.slice(-HASH_HEX_CHARS);
|
||||
const { _hashListed } = require("../src/shared/phishingDomains");
|
||||
expect(_hashListed(first)).toBe(true);
|
||||
expect(_hashListed(last)).toBe(true);
|
||||
expect(_hashListed("0".repeat(HASH_HEX_CHARS))).toBe(false);
|
||||
expect(_hashListed("f".repeat(HASH_HEX_CHARS))).toBe(false);
|
||||
});
|
||||
});
|
||||
|
||||
describe("phishingDomains", () => {
|
||||
describe("vendored blocklist", () => {
|
||||
test("vendored blacklist is loaded from bundled JSON", () => {
|
||||
// The vendored blocklist should have a large number of entries
|
||||
expect(_getVendoredBlacklistSize()).toBeGreaterThan(100000);
|
||||
});
|
||||
|
||||
test("detects domains from vendored blacklist", () => {
|
||||
// These are well-known phishing domains in the vendored list
|
||||
expect(isPhishingDomain("hopprotocol.pro")).toBe(true);
|
||||
expect(isPhishingDomain("blast-pools.pages.dev")).toBe(true);
|
||||
});
|
||||
|
||||
test("getBlocklistSize includes vendored entries", () => {
|
||||
expect(getBlocklistSize()).toBeGreaterThan(100000);
|
||||
});
|
||||
});
|
||||
|
||||
describe("hostnameVariants", () => {
|
||||
describe("hostnameVariants", () => {
|
||||
test("returns exact hostname plus parent domains", () => {
|
||||
const variants = hostnameVariants("sub.evil.com");
|
||||
expect(variants).toEqual(["sub.evil.com", "evil.com"]);
|
||||
expect(hostnameVariants("sub.evil.com")).toEqual([
|
||||
"sub.evil.com",
|
||||
"evil.com",
|
||||
]);
|
||||
});
|
||||
|
||||
test("returns just the hostname for a bare domain", () => {
|
||||
const variants = hostnameVariants("example.com");
|
||||
expect(variants).toEqual(["example.com"]);
|
||||
expect(hostnameVariants("example.com")).toEqual(["example.com"]);
|
||||
});
|
||||
|
||||
test("handles deep subdomain chains", () => {
|
||||
const variants = hostnameVariants("a.b.c.d.com");
|
||||
expect(variants).toEqual([
|
||||
expect(hostnameVariants("a.b.c.d.com")).toEqual([
|
||||
"a.b.c.d.com",
|
||||
"b.c.d.com",
|
||||
"c.d.com",
|
||||
@@ -96,478 +131,89 @@ describe("phishingDomains", () => {
|
||||
});
|
||||
|
||||
test("lowercases hostnames", () => {
|
||||
const variants = hostnameVariants("Evil.COM");
|
||||
expect(variants).toEqual(["evil.com"]);
|
||||
});
|
||||
});
|
||||
|
||||
describe("delta computation via loadConfig", () => {
|
||||
test("loadConfig computes delta of new entries not in vendored list", () => {
|
||||
loadConfig({
|
||||
blacklist: [
|
||||
"brand-new-scam-site-xyz123.com",
|
||||
"hopprotocol.pro", // already in vendored
|
||||
],
|
||||
});
|
||||
// Only the new domain should be in the delta
|
||||
expect(
|
||||
_getDeltaBlacklist().has("brand-new-scam-site-xyz123.com"),
|
||||
).toBe(true);
|
||||
expect(_getDeltaBlacklist().has("hopprotocol.pro")).toBe(false);
|
||||
expect(getDeltaSize()).toBe(1);
|
||||
});
|
||||
|
||||
test("re-loading config replaces previous delta", () => {
|
||||
loadConfig({
|
||||
blacklist: ["first-scam-xyz.com"],
|
||||
});
|
||||
expect(isPhishingDomain("first-scam-xyz.com")).toBe(true);
|
||||
|
||||
loadConfig({
|
||||
blacklist: ["second-scam-xyz.com"],
|
||||
});
|
||||
expect(isPhishingDomain("first-scam-xyz.com")).toBe(false);
|
||||
expect(isPhishingDomain("second-scam-xyz.com")).toBe(true);
|
||||
});
|
||||
|
||||
test("getBlocklistSize includes both vendored and delta", () => {
|
||||
const baseSize = getBlocklistSize();
|
||||
loadConfig({
|
||||
blacklist: ["delta-only-scam-xyz.com"],
|
||||
});
|
||||
expect(getBlocklistSize()).toBe(baseSize + 1);
|
||||
});
|
||||
});
|
||||
|
||||
describe("isPhishingDomain with delta + vendored", () => {
|
||||
test("detects domain from delta blacklist", () => {
|
||||
loadConfig({
|
||||
blacklist: ["fresh-scam-xyz.com"],
|
||||
});
|
||||
expect(isPhishingDomain("fresh-scam-xyz.com")).toBe(true);
|
||||
});
|
||||
|
||||
test("detects domain from vendored blacklist", () => {
|
||||
// No delta loaded — vendored still works
|
||||
expect(isPhishingDomain("hopprotocol.pro")).toBe(true);
|
||||
});
|
||||
|
||||
test("returns false for clean domains", () => {
|
||||
expect(isPhishingDomain("etherscan.io")).toBe(false);
|
||||
expect(isPhishingDomain("example.com")).toBe(false);
|
||||
});
|
||||
|
||||
test("detects subdomain of blacklisted domain (vendored)", () => {
|
||||
expect(isPhishingDomain("app.hopprotocol.pro")).toBe(true);
|
||||
});
|
||||
|
||||
test("detects subdomain of blacklisted domain (delta)", () => {
|
||||
loadConfig({
|
||||
blacklist: ["delta-phish-xyz.com"],
|
||||
});
|
||||
expect(isPhishingDomain("sub.delta-phish-xyz.com")).toBe(true);
|
||||
});
|
||||
|
||||
test("case-insensitive matching", () => {
|
||||
loadConfig({
|
||||
blacklist: ["Delta-Scam-XYZ.COM"],
|
||||
});
|
||||
expect(isPhishingDomain("delta-scam-xyz.com")).toBe(true);
|
||||
expect(isPhishingDomain("DELTA-SCAM-XYZ.COM")).toBe(true);
|
||||
});
|
||||
|
||||
test("returns false for empty/null hostname", () => {
|
||||
expect(isPhishingDomain("")).toBe(false);
|
||||
expect(isPhishingDomain(null)).toBe(false);
|
||||
});
|
||||
|
||||
test("handles config with no blacklist key", () => {
|
||||
loadConfig({});
|
||||
expect(getDeltaSize()).toBe(0);
|
||||
// Vendored list still works
|
||||
expect(isPhishingDomain("hopprotocol.pro")).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe("extension storage persistence", () => {
|
||||
test("delta is persisted to extension storage, not localStorage", async () => {
|
||||
await loadConfig({
|
||||
blacklist: ["persisted-scam-xyz.com"],
|
||||
});
|
||||
const stored = storageStore[DELTA_STORAGE_KEY];
|
||||
expect(stored).toBeDefined();
|
||||
expect(stored.blacklist).toContain("persisted-scam-xyz.com");
|
||||
});
|
||||
|
||||
test("the fetch timestamp is persisted alongside the delta", async () => {
|
||||
const before = Date.now();
|
||||
await loadConfig({ blacklist: ["timestamped-scam-xyz.com"] });
|
||||
const stored = storageStore[DELTA_STORAGE_KEY];
|
||||
expect(typeof stored.lastFetchTime).toBe("number");
|
||||
expect(stored.lastFetchTime).toBeGreaterThanOrEqual(before);
|
||||
});
|
||||
|
||||
test("an oversized delta is dropped entirely, timestamp included", async () => {
|
||||
// A record above the 256 KiB cap is not worth keeping; the
|
||||
// timestamp goes with it so the next start re-fetches rather than
|
||||
// claiming freshness for a delta that was never stored.
|
||||
const huge = [];
|
||||
for (let i = 0; i < 20000; i++) {
|
||||
huge.push(`oversize-scam-${i}-xyzxyzxyzxyzxyz.com`);
|
||||
}
|
||||
await loadConfig({ blacklist: huge });
|
||||
expect(storageStore[DELTA_STORAGE_KEY]).toBeUndefined();
|
||||
});
|
||||
|
||||
test("delta is cleared on _reset", () => {
|
||||
loadConfig({
|
||||
blacklist: ["temp-scam-xyz.com"],
|
||||
});
|
||||
expect(getDeltaSize()).toBe(1);
|
||||
_reset();
|
||||
expect(getDeltaSize()).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe("real-world blocklist patterns", () => {
|
||||
test("detects known phishing domains from vendored list", () => {
|
||||
expect(isPhishingDomain("uniswap-trade.web.app")).toBe(true);
|
||||
expect(isPhishingDomain("hopprotocol.pro")).toBe(true);
|
||||
expect(isPhishingDomain("blast-pools.pages.dev")).toBe(true);
|
||||
});
|
||||
|
||||
test("does not flag legitimate domains", () => {
|
||||
expect(isPhishingDomain("opensea.io")).toBe(false);
|
||||
expect(isPhishingDomain("etherscan.io")).toBe(false);
|
||||
});
|
||||
expect(hostnameVariants("Evil.COM")).toEqual(["evil.com"]);
|
||||
});
|
||||
});
|
||||
|
||||
describe("phishing list across a service worker restart", () => {
|
||||
beforeEach(() => {
|
||||
clearStorage();
|
||||
jest.resetModules();
|
||||
describe("domain hashing", () => {
|
||||
test("a digest is the declared width of lowercase hex", () => {
|
||||
const hash = hashDomain("example.com");
|
||||
expect(hash).toHaveLength(HASH_HEX_CHARS);
|
||||
expect(hash).toMatch(/^[0-9a-f]+$/);
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
delete global.fetch;
|
||||
test("hashing is case-insensitive, so lookups are too", () => {
|
||||
expect(hashDomain("Evil.COM")).toBe(hashDomain("evil.com"));
|
||||
});
|
||||
|
||||
test("a revived worker restores the persisted delta without re-fetching", async () => {
|
||||
const first = require("../src/shared/phishingDomains");
|
||||
await first.loadConfig({ blacklist: ["restart-scam-xyz.com"] });
|
||||
|
||||
const revived = restartWorker();
|
||||
// Nothing in memory yet — this is a brand new module instance.
|
||||
expect(revived.getDeltaSize()).toBe(0);
|
||||
|
||||
global.fetch = jest.fn();
|
||||
await revived.initPhishingList();
|
||||
|
||||
expect(global.fetch).not.toHaveBeenCalled();
|
||||
expect(revived.getDeltaSize()).toBe(1);
|
||||
expect(revived.isPhishingDomain("restart-scam-xyz.com")).toBe(true);
|
||||
});
|
||||
|
||||
test("repeated wakes inside the cache window never re-fetch", async () => {
|
||||
const first = require("../src/shared/phishingDomains");
|
||||
await first.loadConfig({ blacklist: ["no-storm-scam-xyz.com"] });
|
||||
|
||||
global.fetch = jest.fn();
|
||||
for (let i = 0; i < 5; i++) {
|
||||
const revived = restartWorker();
|
||||
await revived.initPhishingList();
|
||||
}
|
||||
expect(global.fetch).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
test("a persisted timestamp older than the TTL causes a fetch on startup", async () => {
|
||||
const first = require("../src/shared/phishingDomains");
|
||||
await first.loadConfig({ blacklist: ["stale-scam-xyz.com"] });
|
||||
|
||||
// Age the persisted record past the 24-hour TTL.
|
||||
storageStore[first.DELTA_STORAGE_KEY].lastFetchTime =
|
||||
Date.now() - first.CACHE_TTL_MS - 1000;
|
||||
|
||||
const revived = restartWorker();
|
||||
global.fetch = jest.fn(async () => ({
|
||||
ok: true,
|
||||
json: async () => ({ blacklist: ["refreshed-scam-xyz.com"] }),
|
||||
}));
|
||||
await revived.initPhishingList();
|
||||
|
||||
expect(global.fetch).toHaveBeenCalledTimes(1);
|
||||
expect(revived.isPhishingDomain("refreshed-scam-xyz.com")).toBe(true);
|
||||
expect(revived.isPhishingDomain("stale-scam-xyz.com")).toBe(false);
|
||||
});
|
||||
|
||||
test("a first start with nothing persisted fetches immediately", async () => {
|
||||
const fresh = restartWorker();
|
||||
global.fetch = jest.fn(async () => ({
|
||||
ok: true,
|
||||
json: async () => ({ blacklist: ["first-run-scam-xyz.com"] }),
|
||||
}));
|
||||
await fresh.initPhishingList();
|
||||
|
||||
expect(global.fetch).toHaveBeenCalledTimes(1);
|
||||
expect(fresh.isPhishingDomain("first-run-scam-xyz.com")).toBe(true);
|
||||
});
|
||||
|
||||
test("updatePhishingList honours the persisted timestamp on its own", async () => {
|
||||
// The startup path calls updatePhishingList() directly, so it must
|
||||
// load persisted state itself rather than relying on anything else
|
||||
// having finished first.
|
||||
const first = require("../src/shared/phishingDomains");
|
||||
await first.loadConfig({ blacklist: ["alarm-tick-scam-xyz.com"] });
|
||||
|
||||
const revived = restartWorker();
|
||||
global.fetch = jest.fn();
|
||||
await revived.updatePhishingList();
|
||||
|
||||
expect(global.fetch).not.toHaveBeenCalled();
|
||||
expect(revived.isPhishingDomain("alarm-tick-scam-xyz.com")).toBe(true);
|
||||
test("different domains get different digests", () => {
|
||||
expect(hashDomain("evil.com")).not.toBe(hashDomain("evil.org"));
|
||||
});
|
||||
});
|
||||
|
||||
// The alarm period alone must set the cadence. lastFetchTime is stamped when
|
||||
// the fetch completes, so it lands one fetch latency after the alarm that
|
||||
// caused it; a freshness guard timed to the alarm period therefore vetoes
|
||||
// every scheduled tick and halves the real refresh rate. These tests measure
|
||||
// the interval between fetches that actually happened.
|
||||
describe("phishing refresh steady-state cadence", () => {
|
||||
const { PHISHING_REFRESH_PERIOD_MINUTES } = require("../src/shared/alarms");
|
||||
const PERIOD_MS = PHISHING_REFRESH_PERIOD_MINUTES * 60 * 1000;
|
||||
// A blocklist that silently matches nothing is the failure this module must not
|
||||
// have, so each way of breaking the artifact is required to throw at load. The
|
||||
// generator is the only thing that writes this file, but "the generator is
|
||||
// correct" is not something the shipped extension can check at runtime — this
|
||||
// is what makes a format drift a build failure rather than a silent one.
|
||||
describe("a malformed artifact fails loudly", () => {
|
||||
const GOOD = {
|
||||
algorithm: "sha256",
|
||||
hashHexChars: HASH_HEX_CHARS,
|
||||
count: 2,
|
||||
hashes: "0".repeat(HASH_HEX_CHARS) + "1".repeat(HASH_HEX_CHARS),
|
||||
};
|
||||
|
||||
let clockSpy;
|
||||
let now;
|
||||
|
||||
beforeEach(() => {
|
||||
clearStorage();
|
||||
jest.resetModules();
|
||||
now = Date.UTC(2026, 0, 1, 0, 0, 0);
|
||||
clockSpy = jest.spyOn(Date, "now").mockImplementation(() => now);
|
||||
function loadWith(artifact) {
|
||||
let mod;
|
||||
jest.isolateModules(() => {
|
||||
jest.doMock(
|
||||
"../src/shared/phishingBlocklist.json",
|
||||
() => artifact,
|
||||
{
|
||||
virtual: false,
|
||||
},
|
||||
);
|
||||
mod = require("../src/shared/phishingDomains");
|
||||
});
|
||||
return mod;
|
||||
}
|
||||
|
||||
afterEach(() => {
|
||||
clockSpy.mockRestore();
|
||||
delete global.fetch;
|
||||
jest.dontMock("../src/shared/phishingBlocklist.json");
|
||||
});
|
||||
|
||||
function fetchStub(latencyMs, seen) {
|
||||
return jest.fn(async () => {
|
||||
seen.push(now);
|
||||
// A network fetch takes time, and lastFetchTime is stamped after
|
||||
// it, not when the alarm fired.
|
||||
now += latencyMs;
|
||||
return { ok: true, json: async () => ({ blacklist: [] }) };
|
||||
});
|
||||
}
|
||||
|
||||
test("ten alarm ticks produce ten fetches, one per period", async () => {
|
||||
const fetchedAt = [];
|
||||
global.fetch = fetchStub(5000, fetchedAt);
|
||||
|
||||
const startup = require("../src/shared/phishingDomains");
|
||||
const T0 = now;
|
||||
await startup.initPhishingList();
|
||||
expect(fetchedAt).toEqual([T0]);
|
||||
|
||||
const TICKS = 10;
|
||||
let tickAt = T0 + PERIOD_MS;
|
||||
for (let i = 0; i < TICKS; i++) {
|
||||
now = tickAt;
|
||||
tickAt += PERIOD_MS;
|
||||
// The browser wakes a terminated worker to deliver the alarm, so
|
||||
// every tick starts from cold memory and the persisted record.
|
||||
const revived = restartWorker();
|
||||
await revived.refreshPhishingListOnSchedule();
|
||||
}
|
||||
|
||||
expect(fetchedAt).toHaveLength(TICKS + 1);
|
||||
const intervals = fetchedAt.slice(1).map((t, i) => t - fetchedAt[i]);
|
||||
expect(intervals).toEqual(new Array(TICKS).fill(PERIOD_MS));
|
||||
test("the control artifact loads", () => {
|
||||
expect(loadWith(GOOD).getBlocklistSize()).toBe(2);
|
||||
});
|
||||
|
||||
test("the scheduled tick fetches whatever the last fetch's latency was", async () => {
|
||||
// The alarm fires one period after the previous alarm, which is
|
||||
// `latency` short of one period since the fetch it caused completed.
|
||||
for (const latency of [200, 1000, 5000]) {
|
||||
clearStorage();
|
||||
jest.resetModules();
|
||||
storageStore[DELTA_STORAGE_KEY] = {
|
||||
blacklist: [],
|
||||
lastFetchTime: now - PERIOD_MS + latency,
|
||||
lastAttemptTime: now - PERIOD_MS,
|
||||
};
|
||||
const mod = require("../src/shared/phishingDomains");
|
||||
const fetchedAt = [];
|
||||
global.fetch = fetchStub(latency, fetchedAt);
|
||||
|
||||
await mod.refreshPhishingListOnSchedule();
|
||||
expect(fetchedAt).toHaveLength(1);
|
||||
}
|
||||
});
|
||||
|
||||
test("a worker wake inside the cache window still does not fetch", async () => {
|
||||
// The TTL is not removed, only taken off the scheduled path. Chrome
|
||||
// revives the worker every ~30 seconds and every revival runs the
|
||||
// startup path, so the TTL still has to keep that off the network.
|
||||
storageStore[DELTA_STORAGE_KEY] = {
|
||||
blacklist: [],
|
||||
lastFetchTime: now - PERIOD_MS + 5000,
|
||||
lastAttemptTime: now - PERIOD_MS,
|
||||
};
|
||||
const mod = require("../src/shared/phishingDomains");
|
||||
global.fetch = jest.fn();
|
||||
|
||||
await mod.initPhishingList();
|
||||
expect(global.fetch).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
|
||||
describe("phishing list timestamps that cannot be trusted", () => {
|
||||
let clockSpy;
|
||||
let now;
|
||||
|
||||
beforeEach(() => {
|
||||
clearStorage();
|
||||
jest.resetModules();
|
||||
now = Date.UTC(2026, 0, 1, 0, 0, 0);
|
||||
clockSpy = jest.spyOn(Date, "now").mockImplementation(() => now);
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
clockSpy.mockRestore();
|
||||
delete global.fetch;
|
||||
});
|
||||
|
||||
function okFetch() {
|
||||
return jest.fn(async () => ({
|
||||
ok: true,
|
||||
json: async () => ({ blacklist: ["recovered-scam-xyz.com"] }),
|
||||
}));
|
||||
}
|
||||
|
||||
// jest.resetModules() clears the call record of a jest.fn, and simulating
|
||||
// a worker restart is exactly that call. Anything counted across restarts
|
||||
// has to be counted outside the mock.
|
||||
function countingFetch(counter, response) {
|
||||
return async () => {
|
||||
counter.calls++;
|
||||
return response();
|
||||
};
|
||||
}
|
||||
|
||||
test("a lastFetchTime in the future is discarded rather than trusted", async () => {
|
||||
// Clock skew or a restored profile backup writes one. Every guard
|
||||
// measures `Date.now() - stamp` and only tests the lower bound, so a
|
||||
// stamp a year ahead would suppress updates for a year, and now that
|
||||
// the value is persisted it would outlive every worker.
|
||||
storageStore[DELTA_STORAGE_KEY] = {
|
||||
blacklist: ["poisoned-scam-xyz.com"],
|
||||
lastFetchTime: now + 365 * 24 * 60 * 60 * 1000,
|
||||
lastAttemptTime: 0,
|
||||
};
|
||||
const mod = require("../src/shared/phishingDomains");
|
||||
global.fetch = okFetch();
|
||||
|
||||
await mod.initPhishingList();
|
||||
|
||||
expect(global.fetch).toHaveBeenCalledTimes(1);
|
||||
expect(mod.isPhishingDomain("recovered-scam-xyz.com")).toBe(true);
|
||||
// And the record it leaves behind is sane, so recovery is permanent.
|
||||
expect(
|
||||
storageStore[DELTA_STORAGE_KEY].lastFetchTime,
|
||||
).toBeLessThanOrEqual(now);
|
||||
});
|
||||
|
||||
test("a lastAttemptTime in the future does not suppress the retry", async () => {
|
||||
storageStore[DELTA_STORAGE_KEY] = {
|
||||
lastAttemptTime: now + 365 * 24 * 60 * 60 * 1000,
|
||||
};
|
||||
const mod = require("../src/shared/phishingDomains");
|
||||
global.fetch = okFetch();
|
||||
|
||||
await mod.initPhishingList();
|
||||
expect(global.fetch).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
test("an oversized delta does not re-download on every worker wake", async () => {
|
||||
// The delta and its freshness claim are both dropped, which is right,
|
||||
// but nothing then says a fetch just happened. Chrome cycles the
|
||||
// worker roughly every 30 seconds idle, so without the attempt stamp
|
||||
// this is a full blocklist download per wake, forever.
|
||||
const huge = [];
|
||||
for (let i = 0; i < 20000; i++) {
|
||||
huge.push(`oversize-scam-${i}-xyzxyzxyzxyzxyz.com`);
|
||||
}
|
||||
const counter = { calls: 0 };
|
||||
global.fetch = countingFetch(counter, () => ({
|
||||
ok: true,
|
||||
json: async () => ({ blacklist: huge }),
|
||||
}));
|
||||
|
||||
for (let wake = 0; wake < 4; wake++) {
|
||||
const revived = restartWorker();
|
||||
await revived.initPhishingList();
|
||||
now += 30 * 1000; // idle timeout, worker torn down and revived
|
||||
}
|
||||
|
||||
expect(counter.calls).toBe(1);
|
||||
expect(storageStore[DELTA_STORAGE_KEY].blacklist).toBeUndefined();
|
||||
expect(typeof storageStore[DELTA_STORAGE_KEY].lastAttemptTime).toBe(
|
||||
"number",
|
||||
test("a different digest algorithm throws", () => {
|
||||
expect(() => loadWith({ ...GOOD, algorithm: "md5" })).toThrow(
|
||||
/algorithm/,
|
||||
);
|
||||
});
|
||||
|
||||
test("a failing fetch is not retried on every worker wake either", async () => {
|
||||
const counter = { calls: 0 };
|
||||
global.fetch = countingFetch(counter, () => ({
|
||||
ok: false,
|
||||
status: 503,
|
||||
}));
|
||||
|
||||
for (let wake = 0; wake < 4; wake++) {
|
||||
const revived = restartWorker();
|
||||
await revived.initPhishingList();
|
||||
now += 30 * 1000;
|
||||
}
|
||||
|
||||
expect(counter.calls).toBe(1);
|
||||
test("a different digest width throws", () => {
|
||||
expect(() => loadWith({ ...GOOD, hashHexChars: 8 })).toThrow(
|
||||
/hex characters per entry/,
|
||||
);
|
||||
});
|
||||
|
||||
test("the retry floor expires, so a failure is not permanent", async () => {
|
||||
const {
|
||||
MIN_FETCH_ATTEMPT_INTERVAL_MS,
|
||||
} = require("../src/shared/phishingDomains");
|
||||
const counter = { calls: 0 };
|
||||
global.fetch = countingFetch(counter, () => ({
|
||||
ok: false,
|
||||
status: 503,
|
||||
}));
|
||||
|
||||
await restartWorker().initPhishingList();
|
||||
expect(counter.calls).toBe(1);
|
||||
|
||||
// Still inside the floor: no retry.
|
||||
now += MIN_FETCH_ATTEMPT_INTERVAL_MS - 1000;
|
||||
await restartWorker().initPhishingList();
|
||||
expect(counter.calls).toBe(1);
|
||||
|
||||
// Past it: the extension goes back to the network.
|
||||
now += 2000;
|
||||
await restartWorker().initPhishingList();
|
||||
expect(counter.calls).toBe(2);
|
||||
test("a count that does not match the string length throws", () => {
|
||||
expect(() => loadWith({ ...GOOD, count: 3 })).toThrow(
|
||||
/which is not the/,
|
||||
);
|
||||
});
|
||||
|
||||
test("the scheduled tick ignores the retry floor", async () => {
|
||||
// The alarm period is far above the floor, but the floor exists to
|
||||
// throttle wakes, not the schedule.
|
||||
storageStore[DELTA_STORAGE_KEY] = { lastAttemptTime: now - 1000 };
|
||||
const mod = require("../src/shared/phishingDomains");
|
||||
global.fetch = okFetch();
|
||||
test("a missing hashes string throws", () => {
|
||||
expect(() => loadWith({ ...GOOD, hashes: undefined })).toThrow(
|
||||
/no hashes string/,
|
||||
);
|
||||
});
|
||||
|
||||
await mod.refreshPhishingListOnSchedule();
|
||||
expect(global.fetch).toHaveBeenCalledTimes(1);
|
||||
test("an empty artifact throws rather than matching nothing", () => {
|
||||
expect(() => loadWith({ ...GOOD, count: 0, hashes: "" })).toThrow(
|
||||
/entry count/,
|
||||
);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -384,7 +384,7 @@ describe("the shipped token list", () => {
|
||||
"0xab5eb14c09d416f0ac63661e57edb7aecdb9befa", // Metronome Synth USD
|
||||
],
|
||||
MUSD: [
|
||||
"0xaca92e438df0b2401ff60da7e4337b687a2435da", // MetaMask USD
|
||||
"0xaca92e438df0b2401ff60da7e4337b687a2435da",
|
||||
"0xdd468a1ddc392dcdbef6db6e34e89aa338f9f186", // Mezo USD
|
||||
],
|
||||
JPYC: [
|
||||
|
||||
Reference in New Issue
Block a user