llm-security/tests/scanners/auto-cleaner-rce.test.mjs

// auto-cleaner-rce.test.mjs — Security regression for the v7.8.0 CRITICAL (RCE).
//
// auto-cleaner's validateContent() syntax-checked .mjs/.js/.cjs candidates by shelling
// out: execSync(`node --check "${tmpPath}"`). `tmpPath` derives from the finding's
// `file` field — an untrusted scanned-repo FILENAME. The F-2 guard checks path
// containment (the path must stay inside the target tree) but never strips or quotes
// shell metacharacters, and a filename containing `"` closes the interpolated quote.
//
// A file named `x";<cmd>;".mjs` inside an untrusted repo therefore turned
// `/security clean` (live mode is the documented default) into arbitrary command
// execution on the operator's machine.
//
// This test drops such a file in the scanned tree and asserts the injected command
// never ran. It FAILS while the sink goes through a shell, and PASSES once the call
// is a no-shell spawnSync array.

import { describe, it } from 'node:test';
import assert from 'node:assert/strict';
import { mkdtempSync, mkdirSync, writeFileSync, existsSync, rmSync } from 'node:fs';
import { join } from 'node:path';
import { tmpdir } from 'node:os';
import { resetCounter } from '../../scanners/lib/output.mjs';
import { applyFixes, validateContent } from '../../scanners/auto-cleaner.mjs';

const ZW = String.fromCodePoint(0x200B); // zero-width space — strip_zero_width will remove it

// The payload target goes through $CLEANER_RCE_CANARY because a literal path would
// need `/`, which no filename may contain — the env-var expansion also proves a
// *shell* interpreted the string rather than exec'ing an argv array.
const HOSTILE_NAME = 'x";touch $CLEANER_RCE_CANARY;".mjs';

describe('auto-cleaner command-injection regression (CRITICAL, v7.8.1)', () => {
  // Layer 1 — the sink itself. Exercised directly, because the applyFixes-level
  // metachar guard (layer 2) would otherwise stop the input before it ever reaches
  // validateContent, and the test would pass without proving the shell is gone.
  it('validateContent does not shell-interpret a hostile filename', () => {
    const root = mkdtempSync(join(tmpdir(), 'auto-cleaner-rce-sink-'));
    const canary = join(root, 'pwned');
    try {
      process.env.CLEANER_RCE_CANARY = canary;
      const result = validateContent(join(root, HOSTILE_NAME), 'export const a = 1;\n');

      assert.equal(
        existsSync(canary),
        false,
        'COMMAND INJECTION: validateContent shell-executed a command embedded in the filename',
      );
      assert.equal(result.valid, true, 'syntactically valid content must still validate');
    } finally {
      delete process.env.CLEANER_RCE_CANARY;
      rmSync(root, { recursive: true, force: true });
    }
  });

  // Layer 2 — the belt: such a finding never reaches any sink in the first place.
  it('applyFixes refuses a finding whose filename carries shell metacharacters', async () => {
    const root = mkdtempSync(join(tmpdir(), 'auto-cleaner-rce-'));
    const target = join(root, 'scan-target');
    const canary = join(root, 'pwned');

    try {
      mkdirSync(target, { recursive: true });

      process.env.CLEANER_RCE_CANARY = canary;

      // Zero-width char makes the UNI finding auto-tier AND makes the content actually
      // change, so without the guard this file would flow on into the fix pipeline.
      writeFileSync(
        join(target, HOSTILE_NAME),
        `export const a = 1;${ZW}\n`,
        'utf-8',
      );

      const findings = [{
        id: 'RCE-1',
        scanner: 'UNI',
        title: 'Zero-width characters detected',
        severity: 'high',
        file: HOSTILE_NAME,
      }];

      resetCounter();
      const { fixes } = await applyFixes(target, findings, /* dryRun */ false);

      assert.equal(
        existsSync(canary),
        false,
        'COMMAND INJECTION: a shell command embedded in a scanned filename was executed by auto-cleaner',
      );

      // ...and it must be surfaced as refused, never silently dropped.
      const skipped = fixes.find((x) => x.finding_id === 'RCE-1');
      assert.equal(skipped?.status, 'skipped');
      assert.match(skipped.description, /metacharacters/);
    } finally {
      delete process.env.CLEANER_RCE_CANARY;
      rmSync(root, { recursive: true, force: true });
      rmSync(canary, { force: true });
    }
  });
});