AutistMask/src/shared/symbolSpoof.js

// The known-symbol spoof rule, in one place.
//
// A token that borrows a known symbol from a contract that is not the one
// that symbol belongs to is a spoof, and the wallet hides it.  Three surfaces
// ask that question — the transaction history, the Send token selector and
// the balance list — and they must answer it identically: a token the history
// calls fake while the balance list lists it as a holding is worse than
// either verdict alone, because the balance list is where the user forms
// their belief about what they own (issue #235).
//
// KNOWN_SYMBOLS maps a symbol to the set of lowercased contract addresses
// that may bear it, or to null.  Null means the symbol belongs to the native
// asset, which has no contract at all, so no contract may bear it and every
// one that does is a spoof.  "ETH" is one such entry, and every network's
// `nativeCurrency` in networks.js (`SepoliaETH`) is another, on every network.
//
// The value is a set because a ticker is not unique: seven symbols in the
// bundled list belong to two real contracts each, and answering with one of
// them hid the other one's holders' money (issue #276).  Membership, not
// equality, is therefore the question — but it is the same question, asked of
// a table that can now state the truth.  Every address in a set is one the
// wallet ships as a real token; a contract outside the set is still a spoof.
//
// The symbol is attacker-controlled — it is whatever the ERC-20 contract
// returns — so the lookup is done on a normalized form (issue #260): the
// question is whether the symbol reaches the user's eye as a known one,
// since that is what the user acts on.

const { KNOWN_SYMBOLS } = require("./tokenList");

// Ethereum addresses are case-insensitive: EIP-55 mixed case is a checksum
// over the address, not part of its identity.
function normalizeAddress(addr) {
    return (addr || "").toLowerCase();
}

// The characters that paint nothing; normalizeSymbol below says which they
// are. The signature screen marks them in a personal message
// (src/popup/views/approval.js).
const INVISIBLE_CHARACTERS = /[\p{Cf}\p{Default_Ignorable_Code_Point}\x7F]/gu;

// Fold a symbol onto what a user actually sees, and no further:
//
//   NFKC        collapses compatibility variants that render as the ASCII
//               letters they imitate — fullwidth ETH, styled mathematical
//               letters — and maps the non-ASCII spaces onto U+0020.
//   strip       drops what paints nothing: \p{Cf} plus
//               \p{Default_Ignorable_Code_Point} plus U+007F.  That covers
//               the format characters (zero-width space, joiner and
//               non-joiner, word joiner, soft hyphen, byte-order mark, bidi
//               marks and overrides), the variation selectors, the Hangul
//               fillers, and DELETE.  Removed everywhere, not merely at the
//               ends.
//   trim        removes surrounding whitespace, which HTML collapses:
//               `" ETH "` is painted next to the user's real ETH as `ETH`.
//   toUpperCase makes the comparison case-insensitive, as before.
//
// The rule is "strip what paints nothing".  The Unicode classes are how
// that is spelled, not what it means, which is why U+007F is named on its
// own: it is a control rather than a default-ignorable character, so no
// class here reaches it, yet it paints nothing all the same.  Measured in
// the repo's pinned e2e Chromium (16px sans-serif, plain `ETH` = 32.00px,
// so an invisible prefix leaves 32.00px):
//
//   U+007F, U+3164, U+115F, U+FE0F, U+FE00   32.00px — invisible
//   U+FFA0                                   40.00px — a box
//   U+1160                                   48.00px — a box
//   U+0001, U+0085, U+0090                   48.00px — a box
//
// U+1160 and U+FFA0 are `Default_Ignorable_Code_Point` members that font
// fallback nonetheless draws, and they are stripped anyway: erring toward
// hiding a token that does not look like `ETH` is the harmless direction of
// the two.  The other controls are left alone for the same reason read the
// other way — a symbol carrying a visible box does not reach the eye as
// `ETH`, so filtering it would hide a token the user could not have
// confused with the native asset.
//
// Deliberately not folded, and asserted as open in tests/symbolSpoof.test.js:
// interior whitespace (`E T H` renders as `E T H`, so folding it would filter
// a token nobody could confuse with the native asset), confusables that are
// distinct letters rather than compatibility variants (Cyrillic capital Ie,
// U+0415; Greek capital Epsilon, U+0395), bidi reordering, which needs the
// bidi algorithm rather than a character filter, and the visible controls.
//
// This decides only how the question is asked.  Nothing here changes what a
// surface displays; a token still shows the symbol it reports.
function normalizeSymbol(symbol) {
    return String(symbol || "")
        .normalize("NFKC")
        .replace(INVISIBLE_CHARACTERS, "")
        .trim()
        .toUpperCase();
}

// True when a token bearing `symbol` from contract `contractAddress` is
// impersonating a known symbol.
//
// An empty contract address is the native asset, which is never a spoof:
// this is what keeps the user's real ETH out of the rule, and it holds for
// any symbol that becomes null-mapped later, not just for ETH.
function isSpoofedSymbol(symbol, contractAddress) {
    const contract = normalizeAddress(contractAddress);
    if (!contract) return false;
    const sym = normalizeSymbol(symbol);
    if (!KNOWN_SYMBOLS.has(sym)) return false;
    const legit = KNOWN_SYMBOLS.get(sym);
    if (legit === null) return true;
    return !legit.has(contract);
}

module.exports = {
    INVISIBLE_CHARACTERS,
    isSpoofedSymbol,
};