llm-security/tests/lib/policy-loader.test.mjs
Kjell Tore Guttormsen 6d0f3c31fc
fix(policy): read policy.json only from the caller's own working tree
loadPolicy() read .llm-security/policy.json from whatever root it was
given, and every scanner passes the SCANNED TARGET: scan-orchestrator
(policyRoot = resolve(args.target)), entropy-scanner (thresholds and
suppression patterns), signature-scanner (sig.custom_rules_path and
enabled_families), trigger-scanner (phrase lists) and ast-taint-scanner
(enabled, python_path). A foreign/cloned target could raise its own
entropy thresholds, disable SIG families, supply its own SIG ruleset or
name the interpreter the AST scanner spawns — configuring the scan of
itself. Same defect class as S3b's .llm-security-ignore fix.

Chosen: move isOwnWorkingTree() to scanners/lib/own-working-tree.mjs (one
copy, reused by the orchestrator's ignore-file check) and make
loadPolicy() refuse an EXPLICIT root that is not the caller's own tree —
defaults plus one stderr line, same form as S3b — because one rule in one
function covers every scanner and a future call site cannot forget it.
The IMPLICIT root (CLAUDE_PROJECT_ROOT/cwd, what every hook uses) is the
caller's own project by construction and is read as before.
entropy-scanner's calibration.policy_source no longer reports an ignored
file as its source.

New tests/scanners/policy-scope.test.mjs was red on 0d37f5a (foreign
target: entropy finding silenced, custom SIG rule loaded, findings differ
from the same tree without policy.json, no stderr line) and is green now;
its own-tree scenario (known-positive) is green before and after. The 15
existing policy tests that placed own-tree fixtures under os.tmpdir() now
use tests/helpers/own-tree.mjs (fixture under $HOME, cwd set to it).

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-22 20:15:17 +02:00

147 lines
5.5 KiB
JavaScript

// policy-loader.test.mjs — Tests for policy-as-code loader
import { describe, it, beforeEach, afterEach } from 'node:test';
import assert from 'node:assert/strict';
import { writeFileSync, mkdirSync, rmSync, existsSync } from 'node:fs';
import { join } from 'node:path';
import { homedir } from 'node:os';
import { loadPolicy, getPolicyValue, getDefaultPolicy, _resetCacheForTest } from '../../scanners/lib/policy-loader.mjs';
// S3c: an explicit root is read only when it is the caller's own working
// tree (under cwd, never under os.tmpdir()) — see tests/helpers/own-tree.mjs.
const TEST_ROOT = join(homedir(), `.llm-security-policy-test-${Date.now()}`);
const POLICY_DIR = join(TEST_ROOT, '.llm-security');
const POLICY_FILE = join(POLICY_DIR, 'policy.json');
describe('policy-loader', () => {
let prevCwd;
beforeEach(() => {
_resetCacheForTest();
mkdirSync(POLICY_DIR, { recursive: true });
prevCwd = process.cwd();
process.chdir(TEST_ROOT);
});
afterEach(() => {
process.chdir(prevCwd);
_resetCacheForTest();
try { rmSync(TEST_ROOT, { recursive: true }); } catch {}
});
it('returns defaults when no policy file exists', () => {
rmSync(POLICY_FILE, { force: true });
const policy = loadPolicy(TEST_ROOT);
assert.equal(policy.version, '1.0');
assert.equal(policy.injection.mode, 'block');
assert.equal(policy.trifecta.mode, 'warn');
assert.equal(policy.trifecta.window_size, 20);
});
it('reads and merges valid policy file', () => {
writeFileSync(POLICY_FILE, JSON.stringify({
version: '1.0',
trifecta: { mode: 'off' },
}));
const policy = loadPolicy(TEST_ROOT);
assert.equal(policy.trifecta.mode, 'off');
// Other defaults preserved
assert.equal(policy.trifecta.window_size, 20);
assert.equal(policy.injection.mode, 'block');
});
it('handles partial policy (deep merge preserves defaults)', () => {
writeFileSync(POLICY_FILE, JSON.stringify({
secrets: { additional_patterns: ['CUSTOM_SECRET=\\w+'] },
}));
const policy = loadPolicy(TEST_ROOT);
assert.deepEqual(policy.secrets.additional_patterns, ['CUSTOM_SECRET=\\w+']);
assert.deepEqual(policy.secrets.allowed_paths, []); // default preserved
});
it('caches policy per root', () => {
writeFileSync(POLICY_FILE, JSON.stringify({ trifecta: { mode: 'block' } }));
const p1 = loadPolicy(TEST_ROOT);
// Modify file — should still return cached
writeFileSync(POLICY_FILE, JSON.stringify({ trifecta: { mode: 'off' } }));
const p2 = loadPolicy(TEST_ROOT);
assert.equal(p1, p2); // same reference (cached)
assert.equal(p2.trifecta.mode, 'block'); // original value
});
it('getPolicyValue returns correct values', () => {
writeFileSync(POLICY_FILE, JSON.stringify({
mcp: { volume_threshold_bytes: 500_000 },
}));
const val = getPolicyValue('mcp', 'volume_threshold_bytes', 100_000, TEST_ROOT);
assert.equal(val, 500_000);
});
it('getPolicyValue returns default when key not in policy', () => {
writeFileSync(POLICY_FILE, JSON.stringify({ version: '1.0' }));
const val = getPolicyValue('mcp', 'nonexistent_key', 42, TEST_ROOT);
assert.equal(val, 42);
});
it('handles invalid JSON gracefully', () => {
writeFileSync(POLICY_FILE, 'not valid json!!!');
const policy = loadPolicy(TEST_ROOT);
// Should return defaults without crashing
assert.equal(policy.version, '1.0');
assert.equal(policy.injection.mode, 'block');
});
it('getDefaultPolicy returns a copy', () => {
const d1 = getDefaultPolicy();
const d2 = getDefaultPolicy();
assert.deepEqual(d1, d2);
assert.notEqual(d1, d2); // different references
});
it('default policy matches existing hardcoded values', () => {
const defaults = getDefaultPolicy();
// These must match the hardcoded values in hooks
assert.equal(defaults.injection.mode, 'block');
assert.equal(defaults.trifecta.mode, 'warn');
assert.equal(defaults.trifecta.window_size, 20);
assert.equal(defaults.trifecta.long_horizon_window, 100);
assert.equal(defaults.mcp.volume_threshold_bytes, 100_000);
});
it('default policy includes ci section with null/false defaults', () => {
const defaults = getDefaultPolicy();
assert.equal(defaults.ci.failOn, null);
assert.equal(defaults.ci.compact, false);
});
it('ci section merges correctly from policy file', () => {
writeFileSync(POLICY_FILE, JSON.stringify({
ci: { failOn: 'high' },
}));
const policy = loadPolicy(TEST_ROOT);
assert.equal(policy.ci.failOn, 'high');
assert.equal(policy.ci.compact, false); // default preserved
});
it('ci section allows compact override', () => {
writeFileSync(POLICY_FILE, JSON.stringify({
ci: { failOn: 'critical', compact: true },
}));
const policy = loadPolicy(TEST_ROOT);
assert.equal(policy.ci.failOn, 'critical');
assert.equal(policy.ci.compact, true);
});
it('default policy includes trifecta.escalation_window=5 (D3)', () => {
const defaults = getDefaultPolicy();
assert.equal(defaults.trifecta.escalation_window, 5);
});
it('getPolicyValue survives a scalar section override without throwing (#26)', () => {
// A user writing {"injection": "block"} (scalar instead of object) must
// not crash the "key in sectionObj" lookup with a TypeError.
writeFileSync(POLICY_FILE, JSON.stringify({ injection: 'block' }));
const val = getPolicyValue('injection', 'mode', 'warn', TEST_ROOT);
assert.equal(val, 'warn');
});
});