llm-security/scanners/signature-scanner.mjs

// signature-scanner.mjs — SIG: known-bad-identity signature engine
//
// Detects known-malware *identity* (webshells, reverse shells, cryptominers,
// hacktools) — complementary to the shape-based scanners (entropy/taint).
//
// Differentiator vs raw signature engines (e.g. YARA): every signature regex
// is tested not only against the raw file bytes but also against the project's
// decode pipeline (normalizeForScan -> base64/hex/url/entity/unicode decode,
// foldHomoglyphs, rot13). Obfuscated known-malware that a byte-matcher misses
// is therefore still caught.
//
// OWASP coverage: LLM03 (supply chain) primary; LLM02 (sensitive disclosure).
// Zero external dependencies — Node.js builtins only.

import { readFile } from 'node:fs/promises';
import { join, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { finding, scannerResult } from './lib/output.mjs';
import { readTextFile } from './lib/file-discovery.mjs';
import { normalizeForScan, foldHomoglyphs, rot13 } from './lib/string-utils.mjs';
import { getPolicyValue } from './lib/policy-loader.mjs';

const __dirname = dirname(fileURLToPath(import.meta.url));

// Paths excluded from signature scanning when present under the scan root:
// our own ruleset, test fixtures, and docs all legitimately contain patterns
// that would otherwise self-flag.
const EXCLUDED_PATH_RE = /(^|\/)(knowledge|tests|docs|node_modules)\//i;

const DEFAULT_FAMILIES = ['webshell', 'reverse_shell', 'cryptominer', 'hacktool'];

// Cached, compiled ruleset (loaded once per process).
let _rules = null;

/**
 * Load and compile signatures.json. Each rule's `pattern` is compiled to a
 * case-insensitive RegExp; rules whose pattern fails to compile are dropped.
 * Graceful fallback to an empty ruleset on any load/parse error.
 * @returns {Promise<Array<{id,family,severity,re,description,provenance}>>}
 */
async function loadRules() {
  if (_rules) return _rules;
  const rulesetPath = join(__dirname, '..', 'knowledge', 'signatures.json');
  try {
    const raw = await readFile(rulesetPath, 'utf8');
    const parsed = JSON.parse(raw);
    const compiled = [];
    for (const rule of parsed.rules || []) {
      if (!rule || !rule.id || !rule.pattern) continue;
      let re;
      try {
        re = new RegExp(rule.pattern, 'i');
      } catch {
        continue; // skip uncompilable patterns
      }
      compiled.push({
        id: rule.id,
        family: rule.family || 'unknown',
        severity: rule.severity || 'high',
        re,
        description: rule.description || rule.id,
        provenance: rule.provenance || null,
      });
    }
    _rules = compiled;
  } catch {
    _rules = []; // graceful: no ruleset -> no findings
  }
  return _rules;
}

/** Build the decode-variant set for one file's content (de-duplicated). */
function variantsOf(content) {
  const variants = [{ label: 'raw', text: content }];
  const seen = new Set([content]);
  const add = (label, text) => {
    if (text && !seen.has(text)) { seen.add(text); variants.push({ label, text }); }
  };
  // Trimming before decode lets a base64/hex blob with surrounding whitespace
  // (a trailing newline, indentation) still decode — common in real payloads.
  add('decoded', normalizeForScan(content));
  add('decoded-trimmed', normalizeForScan(content.trim()));
  add('homoglyph-folded', foldHomoglyphs(content));
  add('rot13', rot13(content));
  return variants;
}

/**
 * Scan all discovered files for known-bad signatures.
 *
 * @param {string} targetPath        - Absolute root path being scanned
 * @param {{ files: import('./lib/file-discovery.mjs').FileInfo[] }} discovery
 * @returns {Promise<object>}        - scannerResult envelope
 */
export async function scan(targetPath, discovery) {
  const startMs = Date.now();
  const findings = [];
  let filesScanned = 0;

  try {
    const rules = await loadRules();
    const enabledFamilies = new Set(
      (getPolicyValue('sig', 'enabled_families', DEFAULT_FAMILIES, targetPath) || []).map(f => String(f)),
    );
    const activeRules = rules.filter(r => enabledFamilies.has(r.family));
    if (activeRules.length === 0) {
      return scannerResult('signature-scanner', 'ok', findings, filesScanned, Date.now() - startMs);
    }

    for (const fileInfo of discovery.files) {
      const relPath = String(fileInfo.relPath).replace(/\\/g, '/');
      if (EXCLUDED_PATH_RE.test('/' + relPath)) continue;

      const content = await readTextFile(fileInfo.absPath);
      if (content === null) continue;

      filesScanned++;
      const variants = variantsOf(content);
      const seen = new Set(); // de-dup per (file, rule)

      for (const rule of activeRules) {
        if (seen.has(rule.id)) continue;
        const hit = variants.find(v => rule.re.test(v.text));
        if (!hit) continue;
        seen.add(rule.id);
        const viaDecode = hit.label !== 'raw';
        findings.push(finding({
          scanner: 'SIG',
          severity: rule.severity,
          title: `Known-bad signature: ${rule.family} (${rule.id})`,
          description: `${rule.description}${viaDecode ? ` — matched after decoding (${hit.label} variant), i.e. obfuscated.` : '.'}`,
          file: fileInfo.relPath,
          evidence: `${rule.id} [${rule.family}]${rule.provenance ? ` — ${rule.provenance}` : ''}`,
          owasp: 'LLM03',
          recommendation: `Remove the ${rule.family} payload, or if this is an intentional security sample, exclude its path or disable the "${rule.family}" family in .llm-security/policy.json.`,
        }));
      }
    }

    return scannerResult('signature-scanner', 'ok', findings, filesScanned, Date.now() - startMs);

  } catch (err) {
    return scannerResult('signature-scanner', 'error', findings, filesScanned, Date.now() - startMs, err.message);
  }
}