v1.11.7: secret-file deny list for codebase tools

Ports continue.dev's DEFAULT_SECURITY_IGNORE_FILETYPES + ignored-dir lists
into apps/server/src/services/secret_guard.ts plus a small BooCode
additions block (id_rsa*, *credentials*, .netrc, *.kdbx). Tiny glob-to-
regex matcher; no new prod dep.

view_file hard-refuses via SecretBlockedError. list_dir / grep /
find_files filter their results and surface a pathguard_note string
field with the hidden count — never list the offending paths back.

Named secret_guard.ts (not safety/pathGuard.ts) to avoid collision with
the existing path_guard.ts which already exports a pathGuard() function.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-20 20:55:50 +00:00
parent 85037f000d
commit 863452ae07
3 changed files with 467 additions and 11 deletions

View File

@@ -0,0 +1,198 @@
import { describe, it, expect } from 'vitest';
import {
isSecretPath,
filterSecretEntries,
SecretBlockedError,
DEFAULT_SECURITY_IGNORE_FILETYPES,
} from '../secret_guard.js';
// ---- env / config patterns -------------------------------------------------
describe('isSecretPath — env / config files', () => {
it('matches .env (literal via .env*)', () => {
expect(isSecretPath('.env')).toBe(true);
});
it('matches .env.local (via .env*)', () => {
expect(isSecretPath('.env.local')).toBe(true);
});
it('matches .env.production.local (via .env*)', () => {
expect(isSecretPath('.env.production.local')).toBe(true);
});
it('matches .envrc (via .env*, common direnv config holding secrets)', () => {
expect(isSecretPath('.envrc')).toBe(true);
});
it('matches nested .env (apps/server/.env via basename test)', () => {
expect(isSecretPath('apps/server/.env')).toBe(true);
});
it('case-insensitive: .ENV matches .env*', () => {
expect(isSecretPath('.ENV')).toBe(true);
});
});
// ---- SSH / cert / key patterns --------------------------------------------
describe('isSecretPath — SSH / certs / keys', () => {
it('matches id_rsa (continue.dev literal)', () => {
expect(isSecretPath('id_rsa')).toBe(true);
});
it('matches id_rsa.pub (BooCode addition id_rsa*)', () => {
// continue.dev's literal id_rsa wouldn't match this; BooCode broadens
// because .pub files leak hostnames/usernames and authorized_keys hints.
expect(isSecretPath('id_rsa.pub')).toBe(true);
});
it('matches cert.pem (*.pem)', () => {
expect(isSecretPath('cert.pem')).toBe(true);
});
it('matches private.key (*.key)', () => {
expect(isSecretPath('private.key')).toBe(true);
});
});
// ---- credential patterns ---------------------------------------------------
describe('isSecretPath — credential files (BooCode additions)', () => {
it('matches credentials.json (BooCode *credentials*)', () => {
expect(isSecretPath('credentials.json')).toBe(true);
});
it('matches aws_credentials (BooCode *credentials* — substring match)', () => {
// continue.dev has no `credentials*` pattern. BooCode adds `*credentials*`
// to catch the common `aws_credentials`, `gcp-credentials.yml`, etc.
expect(isSecretPath('aws_credentials')).toBe(true);
});
it('matches .netrc (BooCode addition)', () => {
expect(isSecretPath('.netrc')).toBe(true);
});
it('matches keystore.kdbx (BooCode addition *.kdbx)', () => {
expect(isSecretPath('keystore.kdbx')).toBe(true);
});
});
// ---- directory patterns ----------------------------------------------------
describe('isSecretPath — directory segments (trailing-slash patterns)', () => {
it('matches files under .aws/ via segment test', () => {
expect(isSecretPath('home/user/.aws/credentials')).toBe(true);
});
it('matches files under .ssh/', () => {
expect(isSecretPath('home/user/.ssh/known_hosts')).toBe(true);
});
it('matches files inside any path segment named secrets/', () => {
expect(isSecretPath('apps/server/secrets/api.key')).toBe(true);
});
});
// ---- negatives -------------------------------------------------------------
describe('isSecretPath — negatives', () => {
it('package.json is allowed', () => {
expect(isSecretPath('package.json')).toBe(false);
});
it('README.md is allowed', () => {
expect(isSecretPath('README.md')).toBe(false);
});
it('Login.tsx is allowed (substring "login" doesn\'t trigger anything)', () => {
expect(isSecretPath('src/components/Login.tsx')).toBe(false);
});
it('empty string returns false (defensive)', () => {
expect(isSecretPath('')).toBe(false);
});
it('a directory NAMED "credentials" alone does NOT trigger — only file basenames do', () => {
// Worth pinning: BooCode's `*credentials*` is a basename pattern (no
// trailing `/`), so it tests the leaf filename only. A directory
// literally called "credentials" containing innocuous files (e.g.
// Login.tsx) is fine. This is a deliberate trade-off vs. continue.dev's
// dir-pattern approach — adding `credentials/` as a dir pattern would
// block legitimate code like `src/auth/credentials/Login.tsx`.
expect(isSecretPath('src/auth/credentials/Login.tsx')).toBe(false);
// ...but a file INSIDE that dir whose name includes "credentials" still
// blocks via the basename match:
expect(isSecretPath('src/auth/credentials/credentials.ts')).toBe(true);
});
});
// ---- filterSecretEntries (listing-tools helper) ----------------------------
describe('filterSecretEntries', () => {
it('removes secret entries and reports the count via note string', () => {
const entries = [
{ path: 'src/index.ts' },
{ path: '.env' },
{ path: 'README.md' },
{ path: 'id_rsa' },
{ path: 'apps/server/package.json' },
];
const result = filterSecretEntries(entries, (e) => e.path);
expect(result.kept.map((e) => e.path)).toEqual([
'src/index.ts',
'README.md',
'apps/server/package.json',
]);
expect(result.hidden).toBe(2);
expect(result.note).toBe('[pathGuard: 2 entries hidden by secret-file filter]');
});
it('returns undefined note when nothing was filtered', () => {
const result = filterSecretEntries(
[{ path: 'a.ts' }, { path: 'b.ts' }],
(e) => e.path,
);
expect(result.kept).toHaveLength(2);
expect(result.hidden).toBe(0);
expect(result.note).toBeUndefined();
});
it('uses singular "entry" for a 1-hit filter (cosmetic but worth pinning)', () => {
const result = filterSecretEntries(
[{ path: 'index.ts' }, { path: '.env' }],
(e) => e.path,
);
expect(result.note).toBe('[pathGuard: 1 entry hidden by secret-file filter]');
});
});
// ---- SecretBlockedError ----------------------------------------------------
describe('SecretBlockedError', () => {
it('carries the offending path on .path and in the message', () => {
const err = new SecretBlockedError('apps/server/.env');
expect(err.name).toBe('SecretBlockedError');
expect(err.path).toBe('apps/server/.env');
expect(err.message).toContain('apps/server/.env');
expect(err.message).toContain('pathGuard');
});
});
// ---- contract sanity check -------------------------------------------------
describe('DEFAULT_SECURITY_IGNORE_FILETYPES', () => {
it('exports at least 40 patterns (continue.dev base) and is non-empty', () => {
expect(DEFAULT_SECURITY_IGNORE_FILETYPES.length).toBeGreaterThanOrEqual(40);
});
it('includes all the headline continue.dev entries we tested above', () => {
// Spot-check that the list still carries the patterns whose behavior
// the tests depend on. Catches an accidental list edit that would
// silently degrade coverage.
const set = new Set(DEFAULT_SECURITY_IGNORE_FILETYPES);
for (const pat of ['*.env', '.env*', '*.pem', '*.key', 'id_rsa', '.aws/', '.ssh/']) {
expect(set.has(pat), `missing pattern: ${pat}`).toBe(true);
}
});
});

View File

@@ -0,0 +1,226 @@
// v1.11.7: secret-file guard. Filters paths that commonly contain secrets
// (env files, key/cert files, credential stores) out of tool results, and
// hard-refuses single-path reads of the same. Composes with path_guard.ts:
// pathGuard() proves the path is inside the project root; isSecretPath()
// then proves it's not a known-sensitive filename. Patterns ported from
// continuedev/continue/core/indexing/ignore.ts plus a small BooCode
// additions block (see below).
// Verbatim from continuedev/continue/core/indexing/ignore.ts
// DEFAULT_SECURITY_IGNORE_FILETYPES export. 40 patterns.
const CONTINUE_FILETYPES: ReadonlyArray<string> = [
// Environment and configuration files with secrets
'*.env',
'*.env.*',
'.env*',
'config.json',
'config.yaml',
'config.yml',
'settings.json',
'appsettings.json',
'appsettings.*.json',
// Certificate and key files
'*.key',
'*.pem',
'*.p12',
'*.pfx',
'*.crt',
'*.cer',
'*.jks',
'*.keystore',
'*.truststore',
// Database files that may contain sensitive data
'*.db',
'*.sqlite',
'*.sqlite3',
'*.mdb',
'*.accdb',
// Credential and secret files
'*.secret',
'*.secrets',
'auth.json',
'*.token',
// Backup files that might contain sensitive data
'*.bak',
'*.backup',
'*.old',
'*.orig',
// Docker secrets
'docker-compose.override.yml',
'docker-compose.override.yaml',
// SSH and GPG
'id_rsa',
'id_dsa',
'id_ecdsa',
'id_ed25519',
'*.ppk',
'*.gpg',
];
// Verbatim from continuedev/continue/core/indexing/ignore.ts
// DEFAULT_SECURITY_IGNORE_DIRS export. Trailing "/" semantics: match
// against any path segment that equals the dir name (so files INSIDE the
// dir get blocked even if their leaf name is innocuous, e.g.
// `home/user/.aws/credentials` blocks via the `.aws` segment).
const CONTINUE_DIRS: ReadonlyArray<string> = [
// Environment and configuration directories
'.env/',
'env/',
// Cloud provider credential directories
'.aws/',
'.gcp/',
'.azure/',
'.kube/',
'.docker/',
// Secret directories
'secrets/',
'.secrets/',
'private/',
'.private/',
'certs/',
'certificates/',
'keys/',
'.ssh/',
'.gnupg/',
'.gpg/',
// Temporary directories that might contain sensitive data
'tmp/secrets/',
'temp/secrets/',
'.tmp/',
];
// BooCode additions. continue.dev's list omits some classics — closing the
// gaps below. Each entry has a one-line justification so future audits know
// why it's here and not in the upstream port.
const BOOCODE_ADDITIONS: ReadonlyArray<string> = [
// SSH public keys leak hostnames + usernames. continue.dev's `id_rsa`
// is a literal that doesn't match `id_rsa.pub`; broadening to a glob.
'id_rsa*',
'id_dsa*',
'id_ecdsa*',
'id_ed25519*',
// Wide-net credential pattern. `*credentials*` (not `credentials*`)
// because the leak shape varies: credentials.json, aws_credentials,
// gcp-credentials.yml, etc. Trade-off: also catches files named
// "Credentials.tsx" → those go through view_file's hard-refuse path,
// which is the right outcome (the LLM gets a clear "blocked" signal
// and can ask the user to whitelist if it was a false-positive).
'*credentials*',
// .netrc holds plaintext FTP/HTTP credentials. Standard tooling target.
'.netrc',
// KeePass database. Encrypted at rest but contents are 1:1 secret
// material; never want to feed even ciphertext to a model.
'*.kdbx',
];
export const DEFAULT_SECURITY_IGNORE_FILETYPES: ReadonlyArray<string> = [
...CONTINUE_FILETYPES,
...CONTINUE_DIRS,
...BOOCODE_ADDITIONS,
];
// === glob compilation ======================================================
// Tiny glob-to-regex. No new prod dep — the patterns we ship are simple
// (literal | name* | *.ext | dir/). Covers ~95% of glob spec, which is
// 100% of what this list uses. If patterns ever grow to need `**`, `[]`,
// `{a,b}`, or negation, swap in picomatch.
interface CompiledPattern {
regex: RegExp;
// 'basename' = test against the trailing path component only.
// 'segment' = test against ANY path component (used for `dir/` patterns
// so `home/user/.aws/credentials` blocks via the `.aws` seg).
mode: 'basename' | 'segment';
}
function compile(pattern: string): CompiledPattern {
const isDir = pattern.endsWith('/');
const body = isDir ? pattern.slice(0, -1) : pattern;
// Escape regex specials except * and ?. Don't escape `/` — the patterns
// we accept don't contain it, but if a future pattern does, splitting on
// `/` in the matcher already handles it.
const escaped = body.replace(/[.+^${}()|[\]\\]/g, '\\$&');
const regexBody = escaped.replace(/\*/g, '.*').replace(/\?/g, '.');
return {
regex: new RegExp(`^${regexBody}$`, 'i'),
mode: isDir ? 'segment' : 'basename',
};
}
const COMPILED: ReadonlyArray<CompiledPattern> = DEFAULT_SECURITY_IGNORE_FILETYPES.map(compile);
// === public API ============================================================
// Returns true when `relPath` matches a known-secret pattern. Case-insensitive
// (regex 'i' flag). Always normalize path separators to `/` so Windows-origin
// paths match the same patterns. Empty or root-only paths return false.
export function isSecretPath(relPath: string): boolean {
if (!relPath) return false;
const normalized = relPath.replace(/\\/g, '/');
const segments = normalized.split('/').filter((s) => s.length > 0);
if (segments.length === 0) return false;
const base = segments[segments.length - 1]!;
for (const compiled of COMPILED) {
if (compiled.mode === 'basename') {
if (compiled.regex.test(base)) return true;
} else {
for (const seg of segments) {
if (compiled.regex.test(seg)) return true;
}
}
}
return false;
}
// Error thrown by view_file (or any single-path read) when the resolved
// path matches a secret pattern. Caught by inference.ts executeToolCall
// alongside PathScopeError; the message reaches the LLM verbatim so it
// knows the file was deliberately blocked rather than missing/broken.
export class SecretBlockedError extends Error {
readonly path: string;
constructor(relPath: string) {
super(
`Refused: ${relPath} matches a secret-file pattern and was blocked by pathGuard.`,
);
this.name = 'SecretBlockedError';
this.path = relPath;
}
}
// Helper for listing tools (list_dir / grep / find_files). Filters entries
// by their `.path` (or computed path), returns the filtered list plus a
// note string when anything was hidden. Callers attach the note to a
// `pathguard_note` field on their output shape so the LLM sees it.
//
// Generic over the entry type so each tool can pass its own row shape and
// a `pathOf` extractor. The caller-supplied path is what gets tested —
// usually the project-relative path the tool already computes for output.
export function filterSecretEntries<T>(
entries: ReadonlyArray<T>,
pathOf: (entry: T) => string,
): { kept: T[]; hidden: number; note: string | undefined } {
const kept: T[] = [];
let hidden = 0;
for (const e of entries) {
if (isSecretPath(pathOf(e))) {
hidden += 1;
continue;
}
kept.push(e);
}
const note =
hidden > 0
? `[pathGuard: ${hidden} ${hidden === 1 ? 'entry' : 'entries'} hidden by secret-file filter]`
: undefined;
return { kept, hidden, note };
}

View File

@@ -2,6 +2,7 @@ import { readFile, readdir, stat } from 'node:fs/promises';
import { resolve, basename, relative } from 'node:path'; import { resolve, basename, relative } from 'node:path';
import { z } from 'zod'; import { z } from 'zod';
import { pathGuard, PathScopeError } from './path_guard.js'; import { pathGuard, PathScopeError } from './path_guard.js';
import { isSecretPath, SecretBlockedError, filterSecretEntries } from './secret_guard.js';
import { grep as fileOpsGrep, findFiles as fileOpsFindFiles } from './file_ops.js'; import { grep as fileOpsGrep, findFiles as fileOpsFindFiles } from './file_ops.js';
import { getGitMeta } from './git_meta.js'; import { getGitMeta } from './git_meta.js';
import { findSkills, getSkillBody, getSkillResource } from './skills.js'; import { findSkills, getSkillBody, getSkillResource } from './skills.js';
@@ -63,6 +64,15 @@ export const viewFile: ToolDef<ViewFileInputT> = {
}, },
async execute(input, projectRoot) { async execute(input, projectRoot) {
const real = await pathGuard(projectRoot, input.path); const real = await pathGuard(projectRoot, input.path);
// v1.11.7: secret-file deny check. Test the project-relative path
// (matches the form continue.dev's patterns expect: basenames + dir
// segments). Throw a typed error so executeToolCall in inference.ts
// surfaces a clear "blocked" message to the LLM instead of silently
// returning content the user wanted hidden.
const relPath = relative(projectRoot, real) || basename(real);
if (isSecretPath(relPath)) {
throw new SecretBlockedError(relPath);
}
const s = await stat(real); const s = await stat(real);
if (!s.isFile()) { if (!s.isFile()) {
throw new PathScopeError(`not a file: ${input.path}`); throw new PathScopeError(`not a file: ${input.path}`);
@@ -152,11 +162,21 @@ export const listDir: ToolDef<ListDirInputT> = {
}; };
}) })
); );
// v1.11.7: filter entries whose project-relative path matches a secret
// pattern. Each entry is tested using the project-rel dir + its name
// so the pattern's path/segment semantics work for nested dirs like
// `.aws/`. The count is surfaced via `pathguard_note` — we never list
// the hidden paths (defeats the purpose).
const relDir = relative(projectRoot, real) || '.';
const secretFilter = filterSecretEntries(out, (e) =>
relDir === '.' ? e.name : `${relDir}/${e.name}`,
);
return { return {
path: relative(projectRoot, real) || '.', path: relDir,
entries: out, entries: secretFilter.kept,
total, total: secretFilter.kept.length,
truncated: total > MAX_DIR_ENTRIES, truncated: total > MAX_DIR_ENTRIES,
...(secretFilter.note ? { pathguard_note: secretFilter.note } : {}),
}; };
}, },
}; };
@@ -208,14 +228,21 @@ export const grep: ToolDef<GrepInputT> = {
case_sensitive: input.case_sensitive, case_sensitive: input.case_sensitive,
hidden: input.hidden, hidden: input.hidden,
}); });
return { const reshaped = result.matches.map((m) => ({
matches: result.matches.map((m) => ({
path: m.path, path: m.path,
line: m.line, line: m.line,
content: m.text, content: m.text,
})), }));
total: result.matches.length, // v1.11.7: drop matches whose source file is a known-secret pattern.
// file_ops.grep returns project-relative paths, so we feed them straight
// into isSecretPath. Multiple matches in the same secret file each get
// dropped individually — they all count in the hidden tally.
const secretFilter = filterSecretEntries(reshaped, (m) => m.path);
return {
matches: secretFilter.kept,
total: secretFilter.kept.length,
truncated: result.truncated, truncated: result.truncated,
...(secretFilter.note ? { pathguard_note: secretFilter.note } : {}),
}; };
}, },
}; };
@@ -260,10 +287,15 @@ export const findFiles: ToolDef<FindFilesInputT> = {
path: input.path, path: input.path,
max_results: limit, max_results: limit,
}); });
// v1.11.7: drop paths matching secret patterns. The original `total`
// from file_ops includes pre-truncation count; we report the visible
// count post-filter so the LLM can't infer hidden-count by subtraction.
const secretFilter = filterSecretEntries(result.files, (p) => p);
return { return {
paths: result.files, paths: secretFilter.kept,
total: result.total, total: secretFilter.kept.length,
truncated: result.truncated, truncated: result.truncated,
...(secretFilter.note ? { pathguard_note: secretFilter.note } : {}),
}; };
}, },
}; };