feat: add Etherscan label scraping and MetaMask phishing domain blocklist
All checks were successful
check / check (push) Successful in 22s

- Add etherscanLabels module: scrapes Etherscan address pages for
  phishing/scam labels (Fake_Phishing*, Exploiter, scam warnings).
  Integrated as best-effort async check in addressWarnings.

- Add phishingDomains module: fetches MetaMask's eth-phishing-detect
  blocklist (~231K domains) at runtime, caches in memory, refreshes
  every 24h. Checks hostnames with subdomain matching and whitelist
  overrides.

- Integrate domain phishing checks into all approval flows:
  connection requests, transaction approvals, and signature requests
  show a prominent red warning banner when the requesting site is on
  the MetaMask blocklist.

- Add unit tests for both modules (12 tests for etherscanLabels
  parsing, 15 tests for phishingDomains matching).

Closes #114
This commit is contained in:
user 2026-03-01 05:03:39 -08:00
parent 9eef2ea602
commit 01839d9c47
8 changed files with 594 additions and 0 deletions

View File

@ -12,6 +12,10 @@ const { refreshBalances, getProvider } = require("../shared/balances");
const { debugFetch } = require("../shared/log");
const { decryptWithPassword } = require("../shared/vault");
const { getSignerForAddress } = require("../shared/wallet");
const {
isPhishingDomain,
updatePhishingList,
} = require("../shared/phishingDomains");
const storageApi =
typeof browser !== "undefined"
@ -571,6 +575,10 @@ async function backgroundRefresh() {
setInterval(backgroundRefresh, BACKGROUND_REFRESH_INTERVAL);
// Fetch the MetaMask eth-phishing-detect domain blocklist on startup.
// Refreshes every 24 hours automatically.
updatePhishingList();
// When approval window is closed without a response, treat as rejection
if (windowsApi && windowsApi.onRemoved) {
windowsApi.onRemoved.addListener((windowId) => {
@ -643,6 +651,8 @@ runtime.onMessage.addListener((msg, sender, sendResponse) => {
resp.type = "sign";
resp.signParams = approval.signParams;
}
// Flag if the requesting domain is on the phishing blocklist.
resp.isPhishingDomain = isPhishingDomain(approval.hostname);
sendResponse(resp);
} else {
sendResponse(null);

View File

@ -1149,6 +1149,20 @@
<!-- ============ TRANSACTION APPROVAL ============ -->
<div id="view-approve-tx" class="view hidden">
<h2 class="font-bold mb-2">Transaction Request</h2>
<div
id="approve-tx-phishing-warning"
class="mb-3 p-2 text-xs font-bold hidden"
style="
background: #fee2e2;
color: #991b1b;
border: 2px solid #dc2626;
border-radius: 6px;
"
>
⚠️ PHISHING WARNING: This site is on MetaMask's phishing
blocklist. This transaction may steal your funds. Proceed
with extreme caution.
</div>
<p class="mb-2">
<span id="approve-tx-hostname" class="font-bold"></span>
wants to send a transaction.
@ -1215,6 +1229,20 @@
<!-- ============ SIGNATURE APPROVAL ============ -->
<div id="view-approve-sign" class="view hidden">
<h2 class="font-bold mb-2">Signature Request</h2>
<div
id="approve-sign-phishing-warning"
class="mb-3 p-2 text-xs font-bold hidden"
style="
background: #fee2e2;
color: #991b1b;
border: 2px solid #dc2626;
border-radius: 6px;
"
>
⚠️ PHISHING WARNING: This site is on MetaMask's phishing
blocklist. Signing this message may authorize theft of your
funds. Proceed with extreme caution.
</div>
<p class="mb-2">
<span id="approve-sign-hostname" class="font-bold"></span>
wants you to sign a message.
@ -1284,6 +1312,20 @@
<!-- ============ SITE APPROVAL ============ -->
<div id="view-approve-site" class="view hidden">
<h2 class="font-bold mb-2">Connection Request</h2>
<div
id="approve-site-phishing-warning"
class="mb-3 p-2 text-xs font-bold hidden"
style="
background: #fee2e2;
color: #991b1b;
border: 2px solid #dc2626;
border-radius: 6px;
"
>
⚠️ PHISHING WARNING: This site is on MetaMask's phishing
blocklist. Connecting your wallet may result in loss of
funds. Proceed with extreme caution.
</div>
<div class="mb-3">
<p class="mb-2">
<span id="approve-hostname" class="font-bold"></span>

View File

@ -13,6 +13,7 @@ const { ERC20_ABI } = require("../../shared/constants");
const { TOKEN_BY_ADDRESS } = require("../../shared/tokenList");
const txStatus = require("./txStatus");
const uniswap = require("../../shared/uniswap");
const { isPhishingDomain } = require("../../shared/phishingDomains");
const runtime =
typeof browser !== "undefined" ? browser.runtime : chrome.runtime;
@ -155,7 +156,24 @@ function decodeCalldata(data, toAddress) {
return null;
}
function showPhishingWarning(elementId, hostname, isPhishing) {
const el = $(elementId);
if (!el) return;
// Check both the flag from background and a local re-check
if (isPhishing || isPhishingDomain(hostname)) {
el.classList.remove("hidden");
} else {
el.classList.add("hidden");
}
}
function showTxApproval(details) {
showPhishingWarning(
"approve-tx-phishing-warning",
details.hostname,
details.isPhishingDomain,
);
const toAddr = details.txParams.to;
const token = toAddr ? TOKEN_BY_ADDRESS.get(toAddr.toLowerCase()) : null;
const ethValue = formatEther(details.txParams.value || "0");
@ -323,6 +341,12 @@ function formatTypedDataHtml(jsonStr) {
}
function showSignApproval(details) {
showPhishingWarning(
"approve-sign-phishing-warning",
details.hostname,
details.isPhishingDomain,
);
const sp = details.signParams;
$("approve-sign-hostname").textContent = details.hostname;
@ -382,6 +406,12 @@ function show(id) {
showSignApproval(details);
return;
}
// Site connection approval
showPhishingWarning(
"approve-site-phishing-warning",
details.hostname,
details.isPhishingDomain,
);
$("approve-hostname").textContent = details.hostname;
$("approve-address").innerHTML = approvalAddressHtml(
state.activeAddress,

View File

@ -4,6 +4,7 @@
const { isScamAddress } = require("./scamlist");
const { isBurnAddress } = require("./constants");
const { checkEtherscanLabel } = require("./etherscanLabels");
const { log } = require("./log");
/**
@ -92,6 +93,16 @@ async function getFullWarnings(address, provider, options = {}) {
log.errorf("tx count check failed:", e.message);
}
// Etherscan label check (best-effort async — network failures are silent).
try {
const etherscanWarning = await checkEtherscanLabel(address);
if (etherscanWarning) {
warnings.push(etherscanWarning);
}
} catch (e) {
log.errorf("etherscan label check failed:", e.message);
}
return warnings;
}

View File

@ -0,0 +1,102 @@
// Etherscan address label lookup via page scraping.
// Extension users make the requests directly to Etherscan — no proxy needed.
// This is a best-effort enrichment: network failures return null silently.
const ETHERSCAN_BASE = "https://etherscan.io/address/";
// Patterns in the page title that indicate a flagged address.
// Title format: "Fake_Phishing184810 | Address: 0x... | Etherscan"
const PHISHING_LABEL_PATTERNS = [/^Fake_Phishing/i, /^Phish:/i, /^Exploiter/i];
// Patterns in the page body that indicate a scam/phishing warning.
const SCAM_BODY_PATTERNS = [
/used in a\s+(?:\w+\s+)?phishing scam/i,
/used in a\s+(?:\w+\s+)?scam/i,
/wallet\s+drainer/i,
];
/**
* Parse the Etherscan address page HTML to extract label info.
* Exported for unit testing (no fetch needed).
*
* @param {string} html - Raw HTML of the Etherscan address page.
* @returns {{ label: string|null, isPhishing: boolean, warning: string|null }}
*/
function parseEtherscanPage(html) {
// Extract <title> content
const titleMatch = html.match(/<title[^>]*>([^<]+)<\/title>/i);
let label = null;
let isPhishing = false;
let warning = null;
if (titleMatch) {
const title = titleMatch[1].trim();
// Title: "LABEL | Address: 0x... | Etherscan" or "Address: 0x... | Etherscan"
const labelMatch = title.match(/^(.+?)\s*\|\s*Address:/);
if (labelMatch) {
const candidate = labelMatch[1].trim();
// Only treat as a label if it's not just "Address" (unlabeled addresses)
if (candidate.toLowerCase() !== "address") {
label = candidate;
}
}
}
// Check label against phishing patterns
if (label) {
for (const pat of PHISHING_LABEL_PATTERNS) {
if (pat.test(label)) {
isPhishing = true;
warning = `Etherscan labels this address as "${label}" (Phish/Hack).`;
break;
}
}
}
// Check page body for scam warning banners
if (!isPhishing) {
for (const pat of SCAM_BODY_PATTERNS) {
if (pat.test(html)) {
isPhishing = true;
warning = label
? `Etherscan labels this address as "${label}" and reports it was used in a scam.`
: "Etherscan reports this address was flagged for phishing/scam activity.";
break;
}
}
}
return { label, isPhishing, warning };
}
/**
* Fetch an address page from Etherscan and check for scam/phishing labels.
* Returns a warning object if the address is flagged, or null.
* Network failures return null silently (best-effort check).
*
* @param {string} address - Ethereum address to check.
* @returns {Promise<{type: string, message: string, severity: string}|null>}
*/
async function checkEtherscanLabel(address) {
try {
const resp = await fetch(ETHERSCAN_BASE + address, {
headers: { Accept: "text/html" },
});
if (!resp.ok) return null;
const html = await resp.text();
const result = parseEtherscanPage(html);
if (result.isPhishing) {
return {
type: "etherscan-phishing",
message: result.warning,
severity: "critical",
};
}
return null;
} catch {
// Network errors are expected — Etherscan may rate-limit or block.
return null;
}
}
module.exports = { parseEtherscanPage, checkEtherscanLabel };

View File

@ -0,0 +1,133 @@
// Domain-based phishing detection using MetaMask's eth-phishing-detect blocklist.
// Fetches the blocklist at runtime, caches it in memory, and checks hostnames.
//
// The blocklist source:
// https://github.com/MetaMask/eth-phishing-detect (src/config.json)
//
// The config uses { blacklist: [...], whitelist: [...], fuzzylist: [...] }.
// We check exact hostname and parent-domain matches against the blacklist,
// with whitelist overrides.
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
let blacklistSet = new Set();
let whitelistSet = new Set();
let lastFetchTime = 0;
let fetchPromise = null;
/**
* Load a pre-parsed config into the in-memory sets.
* Used for testing and for loading from cache.
*
* @param {{ blacklist?: string[], whitelist?: string[] }} config
*/
function loadConfig(config) {
blacklistSet = new Set(
(config.blacklist || []).map((d) => d.toLowerCase()),
);
whitelistSet = new Set(
(config.whitelist || []).map((d) => d.toLowerCase()),
);
lastFetchTime = Date.now();
}
/**
* Generate hostname variants for subdomain matching.
* "sub.evil.com" yields ["sub.evil.com", "evil.com"].
*
* @param {string} hostname
* @returns {string[]}
*/
function hostnameVariants(hostname) {
const h = hostname.toLowerCase();
const variants = [h];
const parts = h.split(".");
// Parent domains: a.b.c.d -> b.c.d, c.d
for (let i = 1; i < parts.length - 1; i++) {
variants.push(parts.slice(i).join("."));
}
return variants;
}
/**
* Check if a hostname is on the phishing blocklist.
* Checks exact hostname and all parent domains.
* Whitelisted domains are never flagged.
*
* @param {string} hostname - The hostname to check.
* @returns {boolean}
*/
function isPhishingDomain(hostname) {
if (!hostname) return false;
const variants = hostnameVariants(hostname);
// Whitelist takes priority
for (const v of variants) {
if (whitelistSet.has(v)) return false;
}
for (const v of variants) {
if (blacklistSet.has(v)) return true;
}
return false;
}
/**
* Fetch the latest blocklist from the MetaMask repo.
* De-duplicates concurrent fetches. Results are cached for CACHE_TTL_MS.
*
* @returns {Promise<void>}
*/
async function updatePhishingList() {
// Skip if recently fetched
if (Date.now() - lastFetchTime < CACHE_TTL_MS && blacklistSet.size > 0) {
return;
}
// De-duplicate concurrent calls
if (fetchPromise) return fetchPromise;
fetchPromise = (async () => {
try {
const resp = await fetch(BLOCKLIST_URL);
if (!resp.ok) throw new Error("HTTP " + resp.status);
const config = await resp.json();
loadConfig(config);
} catch {
// Silently fail — we'll retry next time.
} finally {
fetchPromise = null;
}
})();
return fetchPromise;
}
/**
* Return the current blocklist size (for diagnostics).
*
* @returns {number}
*/
function getBlocklistSize() {
return blacklistSet.size;
}
/**
* Reset internal state (for testing).
*/
function _reset() {
blacklistSet = new Set();
whitelistSet = new Set();
lastFetchTime = 0;
fetchPromise = null;
}
module.exports = {
isPhishingDomain,
updatePhishingList,
loadConfig,
getBlocklistSize,
hostnameVariants,
_reset,
};

View File

@ -0,0 +1,100 @@
const { parseEtherscanPage } = require("../src/shared/etherscanLabels");
describe("etherscanLabels", () => {
describe("parseEtherscanPage", () => {
test("detects Fake_Phishing label in title", () => {
const html = `<html><head><title>Fake_Phishing184810 | Address: 0x00000c07...3ea470000 | Etherscan</title></head><body></body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBe("Fake_Phishing184810");
expect(result.isPhishing).toBe(true);
expect(result.warning).toContain("Fake_Phishing184810");
expect(result.warning).toContain("Phish/Hack");
});
test("detects Fake_Phishing with different number", () => {
const html = `<html><head><title>Fake_Phishing5169 | Address: 0x3e0defb8...99a7a8a74 | Etherscan</title></head><body></body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBe("Fake_Phishing5169");
expect(result.isPhishing).toBe(true);
});
test("detects Exploiter label", () => {
const html = `<html><head><title>Exploiter 42 | Address: 0xabcdef...1234 | Etherscan</title></head><body></body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBe("Exploiter 42");
expect(result.isPhishing).toBe(true);
});
test("detects scam warning in body text", () => {
const html =
`<html><head><title>Address: 0xabcdef...1234 | Etherscan</title></head>` +
`<body>There are reports that this address was used in a Phishing scam.</body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBeNull();
expect(result.isPhishing).toBe(true);
expect(result.warning).toContain("phishing/scam");
});
test("detects scam warning with label in body", () => {
const html =
`<html><head><title>SomeScammer | Address: 0xabcdef...1234 | Etherscan</title></head>` +
`<body>There are reports that this address was used in a scam.</body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBe("SomeScammer");
expect(result.isPhishing).toBe(true);
expect(result.warning).toContain("SomeScammer");
});
test("returns clean result for legitimate address", () => {
const html = `<html><head><title>vitalik.eth | Address: 0xd8dA6BF2...37aA96045 | Etherscan</title></head><body>Overview</body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBe("vitalik.eth");
expect(result.isPhishing).toBe(false);
expect(result.warning).toBeNull();
});
test("returns clean result for unlabeled address", () => {
const html = `<html><head><title>Address: 0x1234567890...abcdef | Etherscan</title></head><body>Overview</body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBeNull();
expect(result.isPhishing).toBe(false);
expect(result.warning).toBeNull();
});
test("handles exchange labels correctly (not phishing)", () => {
const html = `<html><head><title>Coinbase 10 | Address: 0xa9d1e08c...b81d3e43 | Etherscan</title></head><body>Overview</body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBe("Coinbase 10");
expect(result.isPhishing).toBe(false);
});
test("handles contract names correctly (not phishing)", () => {
const html = `<html><head><title>Beacon Deposit Contract | Address: 0x00000000...03d7705Fa | Etherscan</title></head><body>Overview</body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBe("Beacon Deposit Contract");
expect(result.isPhishing).toBe(false);
});
test("handles empty HTML gracefully", () => {
const result = parseEtherscanPage("");
expect(result.label).toBeNull();
expect(result.isPhishing).toBe(false);
expect(result.warning).toBeNull();
});
test("handles malformed title tag", () => {
const html = `<html><head><title></title></head><body></body></html>`;
const result = parseEtherscanPage(html);
expect(result.label).toBeNull();
expect(result.isPhishing).toBe(false);
});
test("detects wallet drainer warning", () => {
const html =
`<html><head><title>Address: 0xabc...def | Etherscan</title></head>` +
`<body>This is a known wallet drainer contract.</body></html>`;
const result = parseEtherscanPage(html);
expect(result.isPhishing).toBe(true);
});
});
});

View File

@ -0,0 +1,166 @@
const {
isPhishingDomain,
loadConfig,
getBlocklistSize,
hostnameVariants,
_reset,
} = require("../src/shared/phishingDomains");
// Reset state before each test to avoid cross-test contamination.
beforeEach(() => {
_reset();
});
describe("phishingDomains", () => {
describe("hostnameVariants", () => {
test("returns exact hostname plus parent domains", () => {
const variants = hostnameVariants("sub.evil.com");
expect(variants).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"]);
});
test("handles deep subdomain chains", () => {
const variants = hostnameVariants("a.b.c.d.com");
expect(variants).toEqual([
"a.b.c.d.com",
"b.c.d.com",
"c.d.com",
"d.com",
]);
});
test("lowercases hostnames", () => {
const variants = hostnameVariants("Evil.COM");
expect(variants).toEqual(["evil.com"]);
});
});
describe("loadConfig + isPhishingDomain", () => {
test("detects exact blacklisted domain", () => {
loadConfig({
blacklist: ["evil-phishing.com", "scam-swap.xyz"],
whitelist: [],
});
expect(isPhishingDomain("evil-phishing.com")).toBe(true);
expect(isPhishingDomain("scam-swap.xyz")).toBe(true);
});
test("returns false for clean domains", () => {
loadConfig({
blacklist: ["evil-phishing.com"],
whitelist: [],
});
expect(isPhishingDomain("etherscan.io")).toBe(false);
expect(isPhishingDomain("uniswap.org")).toBe(false);
});
test("detects subdomain of blacklisted domain", () => {
loadConfig({
blacklist: ["evil-phishing.com"],
whitelist: [],
});
expect(isPhishingDomain("app.evil-phishing.com")).toBe(true);
expect(isPhishingDomain("sub.app.evil-phishing.com")).toBe(true);
});
test("whitelist overrides blacklist", () => {
loadConfig({
blacklist: ["metamask.io"],
whitelist: ["metamask.io"],
});
expect(isPhishingDomain("metamask.io")).toBe(false);
});
test("whitelist on parent domain overrides blacklist", () => {
loadConfig({
blacklist: ["sub.legit.com"],
whitelist: ["legit.com"],
});
expect(isPhishingDomain("sub.legit.com")).toBe(false);
});
test("case-insensitive matching", () => {
loadConfig({
blacklist: ["Evil-Phishing.COM"],
whitelist: [],
});
expect(isPhishingDomain("evil-phishing.com")).toBe(true);
expect(isPhishingDomain("EVIL-PHISHING.COM")).toBe(true);
});
test("returns false for empty/null hostname", () => {
loadConfig({
blacklist: ["evil.com"],
whitelist: [],
});
expect(isPhishingDomain("")).toBe(false);
expect(isPhishingDomain(null)).toBe(false);
});
test("getBlocklistSize reflects loaded config", () => {
loadConfig({
blacklist: ["a.com", "b.com", "c.com"],
whitelist: ["d.com"],
});
expect(getBlocklistSize()).toBe(3);
});
test("handles config with no blacklist/whitelist keys", () => {
loadConfig({});
expect(isPhishingDomain("anything.com")).toBe(false);
expect(getBlocklistSize()).toBe(0);
});
test("re-loading config replaces previous data", () => {
loadConfig({
blacklist: ["old-scam.com"],
whitelist: [],
});
expect(isPhishingDomain("old-scam.com")).toBe(true);
loadConfig({
blacklist: ["new-scam.com"],
whitelist: [],
});
expect(isPhishingDomain("old-scam.com")).toBe(false);
expect(isPhishingDomain("new-scam.com")).toBe(true);
});
});
describe("real-world MetaMask blocklist patterns", () => {
test("detects known phishing domains from MetaMask list", () => {
loadConfig({
blacklist: [
"uniswap-trade.web.app",
"hopprotocol.pro",
"blast-pools.pages.dev",
],
whitelist: [],
});
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 whitelisted by MetaMask", () => {
loadConfig({
blacklist: ["opensea.pro"],
whitelist: [
"opensea.io",
"metamask.io",
"etherscan.io",
"opensea.pro",
],
});
expect(isPhishingDomain("opensea.io")).toBe(false);
expect(isPhishingDomain("metamask.io")).toBe(false);
expect(isPhishingDomain("etherscan.io")).toBe(false);
// opensea.pro is both blacklisted and whitelisted — whitelist wins
expect(isPhishingDomain("opensea.pro")).toBe(false);
});
});
});