feat: vendor and censor the phishing blocklist at build time (closes #219)

src/shared/domainHash.js

@@ -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,
+};