mirror of
https://github.com/colbymchenry/codegraph.git
synced 2026-11-15 00:01:39 +08:00
A project at the root of a drive, such as a mapped network drive Z:\, a
subst drive or a UNC share root, indexed nothing on Windows: every file
was refused as "Path traversal blocked", and code reads under the root
were refused too. The containment check appended a separator to the root
before comparing, and a root such as C:\ already ends with one, so the
prefix became C:\\ and no path under the root matched. The dead code
report's default file reader had its own copy of the same check, so it
treated every file of such a project as unreadable.
The check now adds a separator only when the root doesn't already end
with one. The dead code reader uses the shared lexical containment check
instead of its own copy.
Validation on Windows 11:
- subst R: onto a two-file fixture, then codegraph init -y --force R:\:
main indexes 0 files ("all 2 files had errors", 2 "Path traversal
blocked"), and validatePathWithinRoot(R:\, a.ts) is null. The fix
indexes both files (6 nodes, 6 edges) and getCode returns both
functions' source. The mapping was removed after each run.
- Dead code report against one R:\ index: main's reader drops the unused
function as unreadable; the fix reports it.
- Tests: 3 new tests fail on main's source and pass with the fix: a file
under the filesystem root (this drive's root here, / on POSIX), path
math under Q:\ and \\server\share\, and read-only realpaths under C:\.
Reported in PR #415 by @Kamilslaoui93; this reimplements the fix
independently.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
980 lines
37 KiB
TypeScript
980 lines
37 KiB
TypeScript
/**
|
||
* Security Tests
|
||
*
|
||
* Tests for P0/P1 security fixes:
|
||
* - FileLock (cross-process locking)
|
||
* - Path traversal prevention
|
||
* - MCP input validation
|
||
* - Atomic writes
|
||
*/
|
||
|
||
import { describe, it, expect, beforeEach, afterEach } from 'vitest';
|
||
import * as fs from 'fs';
|
||
import * as path from 'path';
|
||
import * as os from 'os';
|
||
import { FileLock, validateProjectPath, validatePathWithinRoot, lexicalPathWithinRoot } from '../src/utils';
|
||
import CodeGraph from '../src/index';
|
||
import { ToolHandler, tools, __setLoadCodeGraphForTests } from '../src/mcp/tools';
|
||
import { scanDirectory, isSourceFile } from '../src/extraction';
|
||
import { DatabaseConnection, getDatabasePath } from '../src/db';
|
||
import { QueryBuilder } from '../src/db/queries';
|
||
|
||
function createTempDir(): string {
|
||
return fs.mkdtempSync(path.join(os.tmpdir(), 'codegraph-security-test-'));
|
||
}
|
||
|
||
function cleanupTempDir(dir: string): void {
|
||
if (fs.existsSync(dir)) {
|
||
fs.rmSync(dir, { recursive: true, force: true });
|
||
}
|
||
}
|
||
|
||
describe('FileLock', () => {
|
||
let tempDir: string;
|
||
let lockPath: string;
|
||
|
||
beforeEach(() => {
|
||
tempDir = createTempDir();
|
||
lockPath = path.join(tempDir, 'test.lock');
|
||
});
|
||
|
||
afterEach(() => {
|
||
cleanupTempDir(tempDir);
|
||
});
|
||
|
||
it('should acquire and release a lock', () => {
|
||
const lock = new FileLock(lockPath);
|
||
lock.acquire();
|
||
|
||
expect(fs.existsSync(lockPath)).toBe(true);
|
||
const content = fs.readFileSync(lockPath, 'utf-8').trim();
|
||
expect(parseInt(content, 10)).toBe(process.pid);
|
||
|
||
lock.release();
|
||
expect(fs.existsSync(lockPath)).toBe(false);
|
||
});
|
||
|
||
it('should prevent double acquisition within same process', () => {
|
||
const lock1 = new FileLock(lockPath);
|
||
const lock2 = new FileLock(lockPath);
|
||
|
||
lock1.acquire();
|
||
|
||
// Second lock should fail because our PID is alive
|
||
expect(() => lock2.acquire()).toThrow(/locked by another process/);
|
||
|
||
lock1.release();
|
||
});
|
||
|
||
it('keeps a live holder protected after its lock file is older than two minutes (#1959)', () => {
|
||
const holder = new FileLock(lockPath);
|
||
const contender = new FileLock(lockPath);
|
||
holder.acquire();
|
||
const old = new Date(Date.now() - 3 * 60_000);
|
||
fs.utimesSync(lockPath, old, old);
|
||
|
||
try {
|
||
expect(() => contender.acquire()).toThrow(/locked by another process/);
|
||
expect(fs.readFileSync(lockPath, 'utf8')).toBe(String(process.pid));
|
||
} finally {
|
||
holder.release();
|
||
contender.release();
|
||
}
|
||
expect(fs.existsSync(lockPath)).toBe(false);
|
||
});
|
||
|
||
it('should detect and remove stale locks from dead processes', () => {
|
||
// Write a lock file with a PID that doesn't exist
|
||
// PID 99999999 is extremely unlikely to be a real process
|
||
fs.writeFileSync(lockPath, '99999999');
|
||
|
||
const lock = new FileLock(lockPath);
|
||
// Should succeed because the PID is dead
|
||
expect(() => lock.acquire()).not.toThrow();
|
||
|
||
lock.release();
|
||
});
|
||
|
||
it('should execute function with withLock', () => {
|
||
const lock = new FileLock(lockPath);
|
||
|
||
const result = lock.withLock(() => {
|
||
expect(fs.existsSync(lockPath)).toBe(true);
|
||
return 42;
|
||
});
|
||
|
||
expect(result).toBe(42);
|
||
expect(fs.existsSync(lockPath)).toBe(false);
|
||
});
|
||
|
||
it('should release lock even if function throws', () => {
|
||
const lock = new FileLock(lockPath);
|
||
|
||
expect(() => {
|
||
lock.withLock(() => {
|
||
throw new Error('test error');
|
||
});
|
||
}).toThrow('test error');
|
||
|
||
expect(fs.existsSync(lockPath)).toBe(false);
|
||
});
|
||
|
||
it('should execute async function with withLockAsync', async () => {
|
||
const lock = new FileLock(lockPath);
|
||
|
||
const result = await lock.withLockAsync(async () => {
|
||
expect(fs.existsSync(lockPath)).toBe(true);
|
||
return 'async-result';
|
||
});
|
||
|
||
expect(result).toBe('async-result');
|
||
expect(fs.existsSync(lockPath)).toBe(false);
|
||
});
|
||
|
||
it('should release lock even if async function throws', async () => {
|
||
const lock = new FileLock(lockPath);
|
||
|
||
await expect(
|
||
lock.withLockAsync(async () => {
|
||
throw new Error('async error');
|
||
})
|
||
).rejects.toThrow('async error');
|
||
|
||
expect(fs.existsSync(lockPath)).toBe(false);
|
||
});
|
||
|
||
it('release should be idempotent', () => {
|
||
const lock = new FileLock(lockPath);
|
||
lock.acquire();
|
||
lock.release();
|
||
// Second release should not throw
|
||
expect(() => lock.release()).not.toThrow();
|
||
});
|
||
});
|
||
|
||
describe('Path Traversal Prevention', () => {
|
||
let testDir: string;
|
||
let cg: CodeGraph;
|
||
|
||
beforeEach(async () => {
|
||
testDir = createTempDir();
|
||
|
||
const srcDir = path.join(testDir, 'src');
|
||
fs.mkdirSync(srcDir);
|
||
|
||
fs.writeFileSync(
|
||
path.join(srcDir, 'hello.ts'),
|
||
`export function hello(): string { return "hi"; }\n`
|
||
);
|
||
|
||
cg = CodeGraph.initSync(testDir, {
|
||
config: { include: ['**/*.ts'], exclude: [] },
|
||
});
|
||
await cg.indexAll();
|
||
});
|
||
|
||
afterEach(() => {
|
||
if (cg) cg.close();
|
||
cleanupTempDir(testDir);
|
||
});
|
||
|
||
it('should read code for valid nodes within project', async () => {
|
||
const nodes = cg.getNodesByKind('function');
|
||
const hello = nodes.find((n) => n.name === 'hello');
|
||
expect(hello).toBeDefined();
|
||
|
||
const code = await cg.getCode(hello!.id);
|
||
expect(code).toContain('hello');
|
||
});
|
||
|
||
it('should return null for non-existent node', async () => {
|
||
const code = await cg.getCode('does-not-exist');
|
||
expect(code).toBeNull();
|
||
});
|
||
});
|
||
|
||
// #415: a root that already ends with its separator (a Windows drive root such
|
||
// as a `Z:\` network drive or a `subst` drive, a UNC share root, POSIX `/`) got
|
||
// a second one appended, so no path under it counted as inside it, and a
|
||
// project there indexed no files. Path math, plus read-only realpaths of `C:\`.
|
||
describe('Path containment at a filesystem root (#415)', () => {
|
||
it('counts a file under the filesystem root as inside it', () => {
|
||
const root = path.parse(process.cwd()).root; // `/`, or this drive's root on Windows
|
||
expect(lexicalPathWithinRoot(root, 'a.ts')).toBe(path.join(root, 'a.ts'));
|
||
expect(lexicalPathWithinRoot(root, path.join('src', 'b.ts'))).toBe(path.join(root, 'src', 'b.ts'));
|
||
});
|
||
|
||
it.runIf(process.platform === 'win32')('counts a file under a drive root or a share root as inside it', () => {
|
||
// Neither the drive nor the share has to exist: this is path math only.
|
||
expect(lexicalPathWithinRoot('Q:\\', 'a.ts')).toBe('Q:\\a.ts');
|
||
expect(lexicalPathWithinRoot('q:\\', 'src\\b.ts')).toBe('q:\\src\\b.ts');
|
||
expect(lexicalPathWithinRoot('\\\\server\\share\\', 'a.ts')).toBe('\\\\server\\share\\a.ts');
|
||
// Another drive or another share is still outside.
|
||
expect(lexicalPathWithinRoot('Q:\\', 'C:\\Windows\\win.ini')).toBeNull();
|
||
expect(lexicalPathWithinRoot('\\\\server\\share\\', '\\\\server\\other\\a.ts')).toBeNull();
|
||
});
|
||
|
||
it.runIf(process.platform === 'win32' && fs.existsSync('C:\\Windows'))(
|
||
'lets the realpath check through for a folder under a drive root',
|
||
() => {
|
||
expect(validatePathWithinRoot('C:\\', 'Windows')?.toLowerCase()).toBe('c:\\windows');
|
||
// A path that doesn't exist yet is judged by its nearest existing
|
||
// ancestor, which here is the drive root itself.
|
||
expect(validatePathWithinRoot('C:\\', 'codegraph-no-such-dir-415\\a.ts')).toBe(
|
||
'C:\\codegraph-no-such-dir-415\\a.ts'
|
||
);
|
||
}
|
||
);
|
||
});
|
||
|
||
describe('Symlink escape prevention (#527)', () => {
|
||
// An in-repo symlink whose logical path is inside the project root but whose
|
||
// REAL target escapes the root must never be served. validatePathWithinRoot
|
||
// is the chokepoint both content-serving read sinks go through (codegraph_node
|
||
// includeCode + codegraph_explore source rendering), so it must resolve
|
||
// symlinks, not just compare strings. realpathSync the roots so the test's own
|
||
// expectations don't trip over /tmp -> /private/tmp on macOS.
|
||
let root: string;
|
||
let outside: string;
|
||
|
||
beforeEach(() => {
|
||
root = fs.realpathSync(fs.mkdtempSync(path.join(os.tmpdir(), 'cg-root-')));
|
||
outside = fs.realpathSync(fs.mkdtempSync(path.join(os.tmpdir(), 'cg-outside-')));
|
||
fs.mkdirSync(path.join(root, 'src'));
|
||
fs.writeFileSync(path.join(root, 'src', 'in.ts'), 'export const x = 1;\n');
|
||
fs.mkdirSync(path.join(outside, 'pkg'));
|
||
fs.writeFileSync(path.join(outside, 'pkg', 'secret.txt'), 'TOP-SECRET\n');
|
||
});
|
||
|
||
afterEach(() => {
|
||
fs.rmSync(root, { recursive: true, force: true });
|
||
fs.rmSync(outside, { recursive: true, force: true });
|
||
});
|
||
|
||
// Symlink creation needs privileges on Windows; skip gracefully if it fails.
|
||
const link = (linkPath: string, target: string): boolean => {
|
||
try { fs.symlinkSync(target, linkPath); return true; } catch { return false; }
|
||
};
|
||
|
||
it('allows a real file inside the root (and realpaths consistently)', () => {
|
||
expect(validatePathWithinRoot(root, 'src/in.ts')).not.toBeNull();
|
||
});
|
||
|
||
it('allows a not-yet-existing path inside the root (ENOENT — files about to be written)', () => {
|
||
expect(validatePathWithinRoot(root, 'src/will-write.ts')).not.toBeNull();
|
||
});
|
||
|
||
it('rejects a lexical ../ traversal out of the root', () => {
|
||
expect(validatePathWithinRoot(root, `../${path.basename(outside)}/pkg/secret.txt`)).toBeNull();
|
||
});
|
||
|
||
it('rejects an in-repo symlink to an out-of-root FILE', () => {
|
||
if (!link(path.join(root, 'escape'), path.join(outside, 'pkg', 'secret.txt'))) return;
|
||
expect(validatePathWithinRoot(root, 'escape')).toBeNull();
|
||
});
|
||
|
||
it('rejects a path that escapes through an in-repo symlink to an out-of-root DIR', () => {
|
||
if (!link(path.join(root, 'escapedir'), path.join(outside, 'pkg'))) return;
|
||
expect(validatePathWithinRoot(root, 'escapedir/secret.txt')).toBeNull();
|
||
});
|
||
|
||
it('rejects a missing leaf below an out-of-root directory symlink', () => {
|
||
if (!link(path.join(root, 'escapedir'), path.join(outside, 'pkg'))) return;
|
||
expect(validatePathWithinRoot(root, 'escapedir/not-created-yet/file.txt')).toBeNull();
|
||
});
|
||
|
||
// A directory link that needs no privilege on Windows (a junction), so the
|
||
// cases below run there without Developer Mode; a symlink elsewhere. Each
|
||
// test removes its own link, so nothing recursive ever walks through one.
|
||
const dirLink = (linkPath: string, target: string): void =>
|
||
fs.symlinkSync(target, linkPath, process.platform === 'win32' ? 'junction' : 'dir');
|
||
|
||
it.runIf(process.platform === 'win32')('rejects a missing leaf below an out-of-root directory junction', () => {
|
||
const junction = path.join(root, 'escapejunction');
|
||
dirLink(junction, path.join(outside, 'pkg'));
|
||
try {
|
||
expect(validatePathWithinRoot(root, 'escapejunction/not-created-yet/file.txt')).toBeNull();
|
||
} finally {
|
||
fs.unlinkSync(junction);
|
||
}
|
||
});
|
||
|
||
it('still allows a missing leaf below a directory link that stays WITHIN the root', () => {
|
||
fs.mkdirSync(path.join(root, 'src', 'realdir'));
|
||
const inLink = path.join(root, 'src', 'linkdir');
|
||
dirLink(inLink, path.join(root, 'src', 'realdir'));
|
||
try {
|
||
expect(validatePathWithinRoot(root, 'src/linkdir/new/file.ts')).toBe(
|
||
path.join(root, 'src', 'linkdir', 'new', 'file.ts')
|
||
);
|
||
} finally {
|
||
fs.unlinkSync(inLink);
|
||
}
|
||
});
|
||
|
||
it('rejects every path under a root that does not exist', () => {
|
||
expect(validatePathWithinRoot(path.join(root, 'gone'), 'src/in.ts')).toBeNull();
|
||
});
|
||
|
||
it('still allows an in-repo symlink that stays WITHIN the root (no over-blocking)', () => {
|
||
if (!link(path.join(root, 'src', 'inlink.ts'), path.join(root, 'src', 'in.ts'))) return;
|
||
expect(validatePathWithinRoot(root, 'src/inlink.ts')).not.toBeNull();
|
||
});
|
||
|
||
// The INDEXING read path opts into following in-root symlinks the directory
|
||
// walk already descended into — discovery and the reader must agree, or files
|
||
// reached via an in-root symlink-to-outside fail to index (#935). The lexical
|
||
// `../` guard is NOT waived, and content-serving sinks never pass the flag.
|
||
it('allowSymlinkEscape follows an in-repo symlink to an out-of-root FILE (indexing read)', () => {
|
||
if (!link(path.join(root, 'escape'), path.join(outside, 'pkg', 'secret.txt'))) return;
|
||
expect(validatePathWithinRoot(root, 'escape', { allowSymlinkEscape: true })).not.toBeNull();
|
||
});
|
||
|
||
it('allowSymlinkEscape follows a path through an in-repo out-of-root DIR symlink (indexing read)', () => {
|
||
if (!link(path.join(root, 'escapedir'), path.join(outside, 'pkg'))) return;
|
||
expect(validatePathWithinRoot(root, 'escapedir/secret.txt', { allowSymlinkEscape: true })).not.toBeNull();
|
||
});
|
||
|
||
it('allowSymlinkEscape still allows a missing leaf through an out-of-root DIR link (indexing read)', () => {
|
||
const escapeLink = path.join(root, 'escapedir');
|
||
dirLink(escapeLink, path.join(outside, 'pkg'));
|
||
try {
|
||
expect(
|
||
validatePathWithinRoot(root, 'escapedir/not-created-yet/file.txt', { allowSymlinkEscape: true })
|
||
).not.toBeNull();
|
||
} finally {
|
||
fs.unlinkSync(escapeLink);
|
||
}
|
||
});
|
||
|
||
it('allowSymlinkEscape STILL rejects a lexical ../ traversal (guard not waived)', () => {
|
||
expect(
|
||
validatePathWithinRoot(root, `../${path.basename(outside)}/pkg/secret.txt`, { allowSymlinkEscape: true })
|
||
).toBeNull();
|
||
});
|
||
|
||
it('end-to-end: getCode never serves an out-of-root file reached via a dir symlink', async () => {
|
||
fs.writeFileSync(path.join(outside, 'pkg', 'leak.ts'),
|
||
'export function leaked() { return "LEAKED-ZZZ-9"; }\n');
|
||
if (!link(path.join(root, 'vendored'), path.join(outside, 'pkg'))) return;
|
||
|
||
const cg = CodeGraph.initSync(root, { config: { include: ['**/*.ts'], exclude: [] } });
|
||
try {
|
||
await cg.indexAll();
|
||
// Whether or not extraction followed the dir symlink, NO node may ever
|
||
// yield the out-of-root content through getCode.
|
||
for (const n of cg.getNodesByKind('function')) {
|
||
const code = await cg.getCode(n.id);
|
||
expect(code ?? '').not.toContain('LEAKED-ZZZ-9');
|
||
}
|
||
} finally {
|
||
cg.close();
|
||
}
|
||
});
|
||
|
||
it('end-to-end (#935): indexes source reached through an in-root dir symlink to outside', async () => {
|
||
// The Dota custom-game layout symlinks `game/` and `content/` into an SDK
|
||
// tree outside the repo. Before #935 the batch reader's strict symlink-escape
|
||
// guard blocked every file under them, so nothing indexed — even though the
|
||
// directory walk deliberately followed the symlink to enumerate them. The
|
||
// reader now agrees with discovery: the file indexes.
|
||
fs.writeFileSync(path.join(outside, 'pkg', 'vendored.ts'),
|
||
'export function vendoredHelper() { return "LEAKED-ZZZ-9"; }\n');
|
||
if (!link(path.join(root, 'game'), path.join(outside, 'pkg'))) return;
|
||
|
||
const cg = CodeGraph.initSync(root, { config: { include: ['**/*.ts'], exclude: [] } });
|
||
try {
|
||
await cg.indexAll();
|
||
// The symlinked-in file is now part of the graph...
|
||
const names = cg.getNodesByKind('function').map((n) => n.name);
|
||
expect(names).toContain('vendoredHelper');
|
||
// ...but its out-of-root contents are STILL never served (the #527 sink
|
||
// stays strict — indexing relaxes only the read path, not getCode).
|
||
for (const n of cg.getNodesByKind('function')) {
|
||
expect((await cg.getCode(n.id)) ?? '').not.toContain('LEAKED-ZZZ-9');
|
||
}
|
||
} finally {
|
||
cg.close();
|
||
}
|
||
});
|
||
});
|
||
|
||
describe('validateProjectPath — sensitive directory blocking', () => {
|
||
// POSIX-only: on Windows '/etc' resolves to C:\etc (non-existent), not a
|
||
// sensitive dir — the Windows case is covered by the win32-gated test below.
|
||
it.runIf(process.platform !== 'win32')('blocks POSIX system directories (exact match)', () => {
|
||
expect(validateProjectPath('/')).toMatch(/sensitive system directory/i);
|
||
expect(validateProjectPath('/etc')).toMatch(/sensitive system directory/i);
|
||
});
|
||
|
||
it('allows a normal, existing directory', () => {
|
||
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'cg-validate-'));
|
||
try {
|
||
expect(validateProjectPath(dir)).toBeNull();
|
||
} finally {
|
||
fs.rmSync(dir, { recursive: true, force: true });
|
||
}
|
||
});
|
||
|
||
// SENSITIVE_PATHS stores the Windows entries lowercase and validateProjectPath
|
||
// matches via resolved.toLowerCase(), so 'C:\\Windows' and 'c:\\windows' are
|
||
// both blocked. path.resolve is platform-specific, so this only runs on Windows.
|
||
it.runIf(process.platform === 'win32')(
|
||
'blocks Windows system directories regardless of case',
|
||
() => {
|
||
expect(validateProjectPath('C:\\Windows')).toMatch(/sensitive system directory/i);
|
||
expect(validateProjectPath('c:\\windows')).toMatch(/sensitive system directory/i);
|
||
expect(validateProjectPath('C:\\WINDOWS\\System32')).toMatch(/sensitive system directory/i);
|
||
}
|
||
);
|
||
});
|
||
|
||
/**
|
||
* A directory link any user can make: a junction on Windows (no privilege or
|
||
* Developer Mode needed), a symlink elsewhere.
|
||
*/
|
||
function linkDir(target: string, link: string): void {
|
||
fs.symlinkSync(target, link, process.platform === 'win32' ? 'junction' : 'dir');
|
||
}
|
||
|
||
/** Point `os.homedir()` at `home`: it reads USERPROFILE on Windows, HOME elsewhere. */
|
||
function setHome(home: string | undefined, profile: string | undefined = home): void {
|
||
if (home === undefined) delete process.env.HOME;
|
||
else process.env.HOME = home;
|
||
if (profile === undefined) delete process.env.USERPROFILE;
|
||
else process.env.USERPROFILE = profile;
|
||
}
|
||
|
||
/**
|
||
* A temp folder holding a private home with its own `.ssh` and `.config`, and
|
||
* the links a case makes. Links are removed before the tree, so the cleanup
|
||
* can never walk into a link's target.
|
||
*/
|
||
function sensitiveFixture() {
|
||
const state = {
|
||
tmp: '',
|
||
home: '',
|
||
links: [] as string[],
|
||
savedHome: undefined as string | undefined,
|
||
savedProfile: undefined as string | undefined,
|
||
};
|
||
beforeEach(() => {
|
||
state.tmp = fs.realpathSync.native(fs.mkdtempSync(path.join(os.tmpdir(), 'cg-sensitive-')));
|
||
state.home = path.join(state.tmp, 'home');
|
||
fs.mkdirSync(path.join(state.home, '.ssh'), { recursive: true });
|
||
fs.mkdirSync(path.join(state.home, '.config', 'nvim'), { recursive: true });
|
||
fs.mkdirSync(path.join(state.tmp, 'project'));
|
||
fs.mkdirSync(path.join(state.tmp, 'elsewhere'));
|
||
state.links = [];
|
||
state.savedHome = process.env.HOME;
|
||
state.savedProfile = process.env.USERPROFILE;
|
||
setHome(state.home);
|
||
});
|
||
afterEach(() => {
|
||
setHome(state.savedHome, state.savedProfile);
|
||
for (const link of state.links.reverse()) fs.unlinkSync(link);
|
||
fs.rmSync(state.tmp, { recursive: true, force: true });
|
||
});
|
||
const link = (target: string, at: string): string => {
|
||
linkDir(target, at);
|
||
state.links.push(at);
|
||
return at;
|
||
};
|
||
return { state, link };
|
||
}
|
||
|
||
// #1930: the guard compared the path as typed, so a link to a sensitive folder,
|
||
// a case variant of one (Windows, macOS) or a `\\?\` spelling (Windows) passed.
|
||
describe('validateProjectPath — the folder a path really names (#1930)', () => {
|
||
const { state, link } = sensitiveFixture();
|
||
|
||
it('refuses a link to a sensitive home folder, and the folders under it', () => {
|
||
const elsewhere = path.join(state.tmp, 'elsewhere');
|
||
const ssh = link(path.join(state.home, '.ssh'), path.join(elsewhere, 'ssh'));
|
||
const config = link(path.join(state.home, '.config'), path.join(elsewhere, 'config'));
|
||
|
||
expect(validateProjectPath(ssh)).toMatch(/sensitive directory/i);
|
||
expect(validateProjectPath(config)).toMatch(/sensitive directory/i);
|
||
expect(validateProjectPath(path.join(config, 'nvim'))).toMatch(/sensitive directory/i);
|
||
// The refusal names the folder the link leads to.
|
||
expect(validateProjectPath(ssh)).toContain(path.join(state.home, '.ssh'));
|
||
// A link to an ordinary folder is still a fine project root.
|
||
const project = link(path.join(state.tmp, 'project'), path.join(elsewhere, 'project'));
|
||
expect(validateProjectPath(project)).toBeNull();
|
||
});
|
||
|
||
it('refuses a sensitive home folder that is itself a link, and links to it', () => {
|
||
// ~/.ssh kept in a dotfiles checkout and linked into the home.
|
||
const dotfiles = path.join(state.tmp, 'dotfiles', 'ssh');
|
||
fs.mkdirSync(dotfiles, { recursive: true });
|
||
fs.rmdirSync(path.join(state.home, '.ssh'));
|
||
link(dotfiles, path.join(state.home, '.ssh'));
|
||
|
||
expect(validateProjectPath(dotfiles)).toMatch(/sensitive directory/i);
|
||
const viaLink = link(path.join(state.home, '.ssh'), path.join(state.tmp, 'elsewhere', 'ssh'));
|
||
expect(validateProjectPath(viaLink)).toMatch(/sensitive directory/i);
|
||
});
|
||
|
||
it("refuses a linked home's sensitive folders by their real path", () => {
|
||
const realHome = path.join(state.tmp, 'real-home');
|
||
fs.mkdirSync(path.join(realHome, '.aws'), { recursive: true });
|
||
const linkedHome = link(realHome, path.join(state.tmp, 'linked-home'));
|
||
setHome(linkedHome);
|
||
|
||
expect(validateProjectPath(path.join(realHome, '.aws'))).toMatch(/sensitive directory/i);
|
||
expect(validateProjectPath(path.join(linkedHome, '.aws'))).toMatch(/sensitive directory/i);
|
||
});
|
||
|
||
it.runIf(process.platform === 'win32' || process.platform === 'darwin')(
|
||
'refuses a case variant of a sensitive home folder (case-insensitive file systems)',
|
||
() => {
|
||
expect(validateProjectPath(path.join(state.home, '.SSH'))).toMatch(/sensitive directory/i);
|
||
expect(validateProjectPath(path.join(state.home, '.Config', 'nvim'))).toMatch(/sensitive directory/i);
|
||
expect(validateProjectPath(path.join(state.home.toUpperCase(), '.config'))).toMatch(
|
||
/sensitive directory/i
|
||
);
|
||
}
|
||
);
|
||
|
||
it.runIf(process.platform === 'win32')('refuses \\\\?\\ and \\\\.\\ spellings of a sensitive folder', () => {
|
||
for (const spelled of [
|
||
`\\\\?\\${path.join(state.home, '.ssh')}`,
|
||
`\\\\.\\${path.join(state.home, '.config')}`,
|
||
`//?/${path.join(state.home, '.ssh').replace(/\\/g, '/')}`,
|
||
]) {
|
||
expect(validateProjectPath(spelled), spelled).toMatch(/sensitive directory/i);
|
||
}
|
||
for (const spelled of ['\\\\?\\C:\\Windows', '\\\\.\\C:\\Windows', '\\\\?\\c:\\windows\\system32', '\\\\?\\C:\\']) {
|
||
expect(validateProjectPath(spelled), spelled).toMatch(/sensitive system directory/i);
|
||
}
|
||
// The prefix on an ordinary folder changes nothing.
|
||
expect(validateProjectPath(`\\\\?\\${path.join(state.tmp, 'project')}`)).toBeNull();
|
||
});
|
||
|
||
it.runIf(process.platform === 'win32' && fs.existsSync('C:\\Windows'))(
|
||
'refuses a junction to a Windows system folder',
|
||
() => {
|
||
const windows = link('C:\\Windows', path.join(state.tmp, 'elsewhere', 'windows'));
|
||
expect(validateProjectPath(windows)).toMatch(/sensitive system directory/i);
|
||
}
|
||
);
|
||
|
||
// On macOS `/etc` is itself a link to `/private/etc`, so this also checks that
|
||
// the system folders are compared by their own real paths.
|
||
it.runIf(process.platform !== 'win32')('refuses a symlink to a system folder', () => {
|
||
const etc = link('/etc', path.join(state.tmp, 'elsewhere', 'etc'));
|
||
expect(validateProjectPath(etc)).toMatch(/sensitive system directory/i);
|
||
});
|
||
|
||
it.runIf(process.platform === 'darwin')('refuses /private/etc, the folder /etc names on macOS', () => {
|
||
expect(validateProjectPath('/private/etc')).toMatch(/sensitive system directory/i);
|
||
});
|
||
});
|
||
|
||
// #1930 through the MCP entry point, against a real index of the folder.
|
||
describe('MCP projectPath into a sensitive folder (#1930)', () => {
|
||
const { state, link } = sensitiveFixture();
|
||
let handler: ToolHandler;
|
||
|
||
beforeEach(async () => {
|
||
const config = path.join(state.home, '.config');
|
||
fs.mkdirSync(path.join(config, 'tool'));
|
||
fs.writeFileSync(
|
||
path.join(config, 'tool', 'secrets.ts'),
|
||
"export function readToken(): string { return 'FAKE-TOKEN-1930'; }\n"
|
||
);
|
||
const indexed = await CodeGraph.init(config, { index: true });
|
||
indexed.close();
|
||
// Without the seam an unrefused path fails to load the engine here instead
|
||
// of opening the folder's index, which would hide a leak.
|
||
__setLoadCodeGraphForTests(CodeGraph);
|
||
handler = new ToolHandler(null);
|
||
});
|
||
|
||
afterEach(async () => {
|
||
await handler.closeAll();
|
||
__setLoadCodeGraphForTests(null);
|
||
});
|
||
|
||
it('refuses a link to the folder, and a missing folder under it', async () => {
|
||
const config = path.join(state.home, '.config');
|
||
const viaLink = link(config, path.join(state.tmp, 'elsewhere', 'config'));
|
||
// A path that doesn't exist skips the up-front check and walks up to the
|
||
// folder's own index, so the root the walk lands on is checked too.
|
||
for (const projectPath of [viaLink, path.join(config, 'no-such-dir'), path.join(viaLink, 'no-such-dir')]) {
|
||
const result = await handler.execute('codegraph_node', {
|
||
symbol: 'readToken',
|
||
includeCode: true,
|
||
projectPath,
|
||
});
|
||
const text = result.content.map((c) => c.text).join('\n');
|
||
expect(result.isError, projectPath).toBe(true);
|
||
expect(text, projectPath).toMatch(/sensitive directory/i);
|
||
expect(text, projectPath).not.toContain('FAKE-TOKEN-1930');
|
||
}
|
||
});
|
||
});
|
||
|
||
describe('MCP Input Validation', () => {
|
||
let testDir: string;
|
||
let cg: CodeGraph;
|
||
let handler: ToolHandler;
|
||
|
||
beforeEach(async () => {
|
||
testDir = createTempDir();
|
||
|
||
const srcDir = path.join(testDir, 'src');
|
||
fs.mkdirSync(srcDir);
|
||
|
||
fs.writeFileSync(
|
||
path.join(srcDir, 'example.ts'),
|
||
`export function exampleFunc(): void {}\nexport class ExampleClass {}\n`
|
||
);
|
||
|
||
cg = CodeGraph.initSync(testDir, {
|
||
config: { include: ['**/*.ts'], exclude: [] },
|
||
});
|
||
await cg.indexAll();
|
||
handler = new ToolHandler(cg);
|
||
});
|
||
|
||
afterEach(() => {
|
||
if (cg) cg.close();
|
||
cleanupTempDir(testDir);
|
||
});
|
||
|
||
it('should reject non-string query in codegraph_search', async () => {
|
||
const result = await handler.execute('codegraph_search', { query: null });
|
||
expect(result.isError).toBe(true);
|
||
expect(result.content[0].text).toContain('non-empty string');
|
||
});
|
||
|
||
it('should reject empty string query in codegraph_search', async () => {
|
||
const result = await handler.execute('codegraph_search', { query: '' });
|
||
expect(result.isError).toBe(true);
|
||
expect(result.content[0].text).toContain('non-empty string');
|
||
});
|
||
|
||
it('should accept valid query in codegraph_search', async () => {
|
||
const result = await handler.execute('codegraph_search', { query: 'example' });
|
||
expect(result.isError).toBeFalsy();
|
||
});
|
||
|
||
it('should clamp limit to valid range in codegraph_search', async () => {
|
||
// Extremely large limit should still work (clamped to 100)
|
||
const result = await handler.execute('codegraph_search', { query: 'example', limit: 999999 });
|
||
expect(result.isError).toBeFalsy();
|
||
});
|
||
|
||
it('should reject non-string symbol in codegraph_callers', async () => {
|
||
const result = await handler.execute('codegraph_callers', { symbol: 123 });
|
||
expect(result.isError).toBe(true);
|
||
expect(result.content[0].text).toContain('non-empty string');
|
||
});
|
||
|
||
it('should reject non-string query in codegraph_explore', async () => {
|
||
const result = await handler.execute('codegraph_explore', { query: undefined });
|
||
expect(result.isError).toBe(true);
|
||
expect(result.content[0].text).toContain('non-empty string');
|
||
});
|
||
|
||
it('should truncate oversized tool output', async () => {
|
||
// Force a huge result set through codegraph_search; the response must be
|
||
// truncated with the sentinel rather than flooding the agent's context.
|
||
const many = Array.from({ length: 3000 }, (_, i) => ({
|
||
node: {
|
||
id: `n${i}`,
|
||
name: `symbol_${i}_${'x'.repeat(40)}`,
|
||
kind: 'function',
|
||
filePath: `src/very/deep/path/file_${i}.ts`,
|
||
startLine: 1,
|
||
endLine: 2,
|
||
language: 'typescript',
|
||
},
|
||
score: 1,
|
||
}));
|
||
const fakeCg = {
|
||
searchNodes: () => many,
|
||
getFile: () => undefined,
|
||
// Search down-ranks generated files, and since #1500 that verdict comes
|
||
// from the index (path convention ∪ content banner) rather than the
|
||
// filename alone. No database here — none of these paths is generated.
|
||
generatedFilePredicate: () => () => false,
|
||
};
|
||
const fakeHandler = new ToolHandler(fakeCg as unknown as CodeGraph);
|
||
|
||
const result = await fakeHandler.execute('codegraph_search', { query: 'x' });
|
||
|
||
expect(result.isError).toBeFalsy();
|
||
expect(result.content[0].text).toContain('... (output truncated)');
|
||
});
|
||
|
||
it('should reject non-string symbol in codegraph_impact', async () => {
|
||
const result = await handler.execute('codegraph_impact', { symbol: [] });
|
||
expect(result.isError).toBe(true);
|
||
});
|
||
|
||
it('should reject non-string symbol in codegraph_node', async () => {
|
||
const result = await handler.execute('codegraph_node', { symbol: false });
|
||
expect(result.isError).toBe(true);
|
||
});
|
||
|
||
it('should reject non-string symbol in codegraph_callees', async () => {
|
||
const result = await handler.execute('codegraph_callees', { symbol: {} });
|
||
expect(result.isError).toBe(true);
|
||
});
|
||
|
||
it('should handle NaN limit gracefully', async () => {
|
||
const result = await handler.execute('codegraph_search', { query: 'example', limit: 'abc' });
|
||
expect(result.isError).toBeFalsy();
|
||
});
|
||
|
||
it('should handle negative limit gracefully', async () => {
|
||
const result = await handler.execute('codegraph_search', { query: 'example', limit: -5 });
|
||
expect(result.isError).toBeFalsy();
|
||
});
|
||
|
||
// #230: getCodeGraph must reject a sensitive system directory passed as
|
||
// projectPath before opening it. The error surfaces through execute()'s
|
||
// catch as an isError result. /etc is sensitive on POSIX; C:\Windows on
|
||
// Windows (path.resolve is platform-specific, so each case is gated).
|
||
it.runIf(process.platform !== 'win32')(
|
||
'rejects a sensitive POSIX projectPath (/etc) via the MCP handler',
|
||
async () => {
|
||
const result = await handler.execute('codegraph_search', {
|
||
query: 'example',
|
||
projectPath: '/etc',
|
||
});
|
||
expect(result.isError).toBe(true);
|
||
expect(result.content[0].text).toMatch(/sensitive system directory/i);
|
||
}
|
||
);
|
||
|
||
it.runIf(process.platform === 'win32')(
|
||
'rejects a sensitive Windows projectPath (C:\\Windows) via the MCP handler',
|
||
async () => {
|
||
const result = await handler.execute('codegraph_search', {
|
||
query: 'example',
|
||
projectPath: 'C:\\Windows',
|
||
});
|
||
expect(result.isError).toBe(true);
|
||
expect(result.content[0].text).toMatch(/sensitive system directory/i);
|
||
}
|
||
);
|
||
});
|
||
|
||
describe('Atomic Writes', () => {
|
||
let tempDir: string;
|
||
|
||
beforeEach(() => {
|
||
tempDir = createTempDir();
|
||
});
|
||
|
||
afterEach(() => {
|
||
cleanupTempDir(tempDir);
|
||
});
|
||
|
||
it('should not leave temp files on success', () => {
|
||
// We test this indirectly through the config-writer module
|
||
// by checking that no .tmp files remain after writing
|
||
const configDir = path.join(tempDir, '.claude');
|
||
fs.mkdirSync(configDir, { recursive: true });
|
||
|
||
const testFile = path.join(configDir, 'test.json');
|
||
// Simulate what atomicWriteFileSync does
|
||
const tmpPath = testFile + '.tmp.' + process.pid;
|
||
fs.writeFileSync(tmpPath, '{"test": true}');
|
||
fs.renameSync(tmpPath, testFile);
|
||
|
||
expect(fs.existsSync(testFile)).toBe(true);
|
||
expect(fs.existsSync(tmpPath)).toBe(false);
|
||
|
||
const content = JSON.parse(fs.readFileSync(testFile, 'utf-8'));
|
||
expect(content.test).toBe(true);
|
||
});
|
||
});
|
||
|
||
describe('Source file detection (isSourceFile)', () => {
|
||
it('selects files by supported extension', () => {
|
||
expect(isSourceFile('src/index.ts')).toBe(true);
|
||
expect(isSourceFile('src/deep/nested/file.ts')).toBe(true);
|
||
expect(isSourceFile('src/component.tsx')).toBe(true);
|
||
expect(isSourceFile('lib/util.js')).toBe(true);
|
||
expect(isSourceFile('src/main.py')).toBe(true);
|
||
});
|
||
|
||
it('rejects unsupported extensions and extensionless files', () => {
|
||
expect(isSourceFile('src/component.css')).toBe(false);
|
||
expect(isSourceFile('README.md')).toBe(false);
|
||
expect(isSourceFile('Makefile')).toBe(false);
|
||
expect(isSourceFile('.gitignore')).toBe(false);
|
||
});
|
||
|
||
it('matches regardless of leading dot directories', () => {
|
||
expect(isSourceFile('.hidden/index.ts')).toBe(true);
|
||
});
|
||
});
|
||
|
||
describe('JSON.parse Error Boundaries in DB', () => {
|
||
let tempDir: string;
|
||
|
||
beforeEach(() => {
|
||
tempDir = createTempDir();
|
||
});
|
||
|
||
afterEach(() => {
|
||
cleanupTempDir(tempDir);
|
||
});
|
||
|
||
it('should not crash when node has malformed JSON in decorators column', () => {
|
||
const dbPath = path.join(tempDir, 'test.db');
|
||
const db = DatabaseConnection.initialize(dbPath);
|
||
const queries = new QueryBuilder(db.getDb());
|
||
|
||
// Insert a node with malformed JSON in the decorators column
|
||
db.getDb().prepare(`
|
||
INSERT INTO nodes (id, kind, name, qualified_name, file_path, language, start_line, end_line, start_column, end_column, decorators, is_exported, is_async, is_static, is_abstract, updated_at)
|
||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
|
||
`).run(
|
||
'test-node-1', 'function', 'myFunc', 'myFunc', 'test.ts', 'typescript',
|
||
1, 5, 0, 0,
|
||
'{not valid json!!!}', // malformed decorators
|
||
0, 0, 0, 0, Date.now()
|
||
);
|
||
|
||
// Should not throw - should return node with undefined decorators
|
||
const node = queries.getNodeById('test-node-1');
|
||
expect(node).not.toBeNull();
|
||
expect(node!.name).toBe('myFunc');
|
||
expect(node!.decorators).toBeUndefined();
|
||
|
||
db.close();
|
||
});
|
||
|
||
it('should not crash when edge has malformed JSON in metadata column', () => {
|
||
const dbPath = path.join(tempDir, 'test.db');
|
||
const db = DatabaseConnection.initialize(dbPath);
|
||
const queries = new QueryBuilder(db.getDb());
|
||
|
||
// Insert two nodes first
|
||
const insertNode = db.getDb().prepare(`
|
||
INSERT INTO nodes (id, kind, name, qualified_name, file_path, language, start_line, end_line, start_column, end_column, is_exported, is_async, is_static, is_abstract, updated_at)
|
||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
|
||
`);
|
||
insertNode.run('node-a', 'function', 'funcA', 'funcA', 'a.ts', 'typescript', 1, 5, 0, 0, 0, 0, 0, 0, Date.now());
|
||
insertNode.run('node-b', 'function', 'funcB', 'funcB', 'b.ts', 'typescript', 1, 5, 0, 0, 0, 0, 0, 0, Date.now());
|
||
|
||
// Insert edge with malformed metadata
|
||
db.getDb().prepare(`
|
||
INSERT INTO edges (source, target, kind, metadata)
|
||
VALUES (?, ?, ?, ?)
|
||
`).run('node-a', 'node-b', 'calls', 'broken json {{{');
|
||
|
||
// Should not throw - should return edge with undefined metadata
|
||
const edges = queries.getOutgoingEdges('node-a');
|
||
expect(edges.length).toBe(1);
|
||
expect(edges[0].source).toBe('node-a');
|
||
expect(edges[0].target).toBe('node-b');
|
||
expect(edges[0].metadata).toBeUndefined();
|
||
|
||
db.close();
|
||
});
|
||
|
||
it('should not crash when file record has malformed JSON in errors column', () => {
|
||
const dbPath = path.join(tempDir, 'test.db');
|
||
const db = DatabaseConnection.initialize(dbPath);
|
||
const queries = new QueryBuilder(db.getDb());
|
||
|
||
// Insert a file with malformed errors JSON
|
||
db.getDb().prepare(`
|
||
INSERT INTO files (path, content_hash, language, size, modified_at, indexed_at, node_count, errors)
|
||
VALUES (?, ?, ?, ?, ?, ?, ?, ?)
|
||
`).run('test.ts', 'abc123', 'typescript', 100, Date.now(), Date.now(), 5, 'not-an-array');
|
||
|
||
// Should not throw - should return file with undefined errors
|
||
const file = queries.getFileByPath('test.ts');
|
||
expect(file).not.toBeNull();
|
||
expect(file!.path).toBe('test.ts');
|
||
expect(file!.errors).toBeUndefined();
|
||
|
||
db.close();
|
||
});
|
||
});
|
||
|
||
describe('Symlink Cycle Detection', () => {
|
||
let tempDir: string;
|
||
|
||
beforeEach(() => {
|
||
tempDir = createTempDir();
|
||
});
|
||
|
||
afterEach(() => {
|
||
cleanupTempDir(tempDir);
|
||
});
|
||
|
||
it('should handle symlink cycle without infinite loop', () => {
|
||
// Create directory structure with a symlink cycle
|
||
const srcDir = path.join(tempDir, 'src');
|
||
fs.mkdirSync(srcDir);
|
||
fs.writeFileSync(path.join(srcDir, 'index.ts'), 'export const x = 1;\n');
|
||
|
||
// Create a symlink from src/loop -> tempDir (parent directory)
|
||
try {
|
||
fs.symlinkSync(tempDir, path.join(srcDir, 'loop'), 'dir');
|
||
} catch {
|
||
// Skip test if symlinks not supported (e.g., Windows without admin)
|
||
return;
|
||
}
|
||
|
||
|
||
// This should complete without hanging
|
||
const files = scanDirectory(tempDir);
|
||
|
||
// Should find the real file but not loop infinitely
|
||
expect(files).toContain('src/index.ts');
|
||
// Should not find duplicates via the symlink path
|
||
const indexFiles = files.filter(f => f.endsWith('index.ts'));
|
||
expect(indexFiles.length).toBe(1);
|
||
});
|
||
|
||
it('should follow valid symlinks to directories', () => {
|
||
// Create source directory with a file
|
||
const realDir = path.join(tempDir, 'real');
|
||
fs.mkdirSync(realDir);
|
||
fs.writeFileSync(path.join(realDir, 'hello.ts'), 'export function hello() {}\n');
|
||
|
||
// Create a symlink to realDir
|
||
const srcDir = path.join(tempDir, 'src');
|
||
fs.mkdirSync(srcDir);
|
||
try {
|
||
fs.symlinkSync(realDir, path.join(srcDir, 'linked'), 'dir');
|
||
} catch {
|
||
return;
|
||
}
|
||
|
||
|
||
const files = scanDirectory(tempDir);
|
||
|
||
// Should find files from both the real dir and via the symlink
|
||
// But deduplicate since they resolve to the same real path
|
||
expect(files.some(f => f.includes('hello.ts'))).toBe(true);
|
||
});
|
||
|
||
it('should skip broken symlinks gracefully', () => {
|
||
const srcDir = path.join(tempDir, 'src');
|
||
fs.mkdirSync(srcDir);
|
||
fs.writeFileSync(path.join(srcDir, 'valid.ts'), 'export const y = 2;\n');
|
||
|
||
try {
|
||
fs.symlinkSync('/nonexistent/path', path.join(srcDir, 'broken'), 'dir');
|
||
} catch {
|
||
return;
|
||
}
|
||
|
||
|
||
// Should not throw
|
||
const files = scanDirectory(tempDir);
|
||
expect(files).toContain('src/valid.ts');
|
||
});
|
||
});
|