@lateos/npm-scan 0.15.1 → 0.15.3

package/backend/detectors/hf-impersonation/index.js

@@ -0,0 +1,396 @@
+import { KNOWN_HF_ORGS } from './known-orgs.js';
+import { jaroWinkler } from './jaro-winkler.js';
+import { simhash, similarity as simhashSimilarity } from './simhash.js';
+
+const HF_URL_PATTERN = /(?:huggingface\.co|hf\.co)\/([^\/\s"'>]+)\/([^\/\s"'>]+)/g;
+const FROM_PRETRAINED_PATTERN = /from_pretrained\(\s*["']([^"']+\/[^"']+)["']/g;
+const HUB_DOWNLOAD_SINGLE = /hub\.download\(\s*["']([^"']+\/[^"']+)["']/g;
+const HUB_DOWNLOAD_DOUBLE = /hub\.download\(\s*["']([^"']+)["']\s*,\s*["']([^"']+)["']/g;
+
+const LIFECYCLE_SCRIPTS = new Set(['postinstall', 'prepare', 'install']);
+const API_BASE = 'https://huggingface.co';
+
+const SEVERITY_SCORE = { none: 0, low: 1, medium: 2, high: 3, critical: 4 };
+const SEVERITY_LABELS = ['none', 'low', 'medium', 'high', 'critical'];
+
+const HF_ARTIFACT_LIBS = new Set(['transformers', 'diffusers', 'sentence-transformers', 'gguf', 'safetensors']);
+const SUSPICIOUS_EXTENSIONS = /\.(exe|msi|bat|ps1|dll)$/i;
+
+const _cache = new Map();
+const CACHE_TTL = 3600 * 1000;
+let _lastFetchTime = 0;
+
+function severityIndex(sev) {
+  return SEVERITY_SCORE[sev] || 0;
+}
+
+function maxSeverity(a, b) {
+  return severityIndex(a) >= severityIndex(b) ? a : b;
+}
+
+function sleep(ms) {
+  return new Promise(r => setTimeout(r, ms));
+}
+
+async function fetchWithCache(url) {
+  const cached = _cache.get(url);
+  if (cached && Date.now() - cached.fetchedAt < CACHE_TTL) {
+    return cached.data;
+  }
+  const now = Date.now();
+  const elapsed = now - _lastFetchTime;
+  if (elapsed < 100) {
+    await sleep(100 - elapsed);
+  }
+  _lastFetchTime = Date.now();
+  let res;
+  try {
+    res = await fetch(url);
+    if (res.status === 429) {
+      const retryAfter = parseInt(res.headers.get('Retry-After') || '5', 10);
+      await sleep(retryAfter * 1000);
+      res = await fetch(url);
+    }
+    if (!res.ok) {
+      console.debug(`HF API warning: ${url} returned ${res.status}`);
+      return null;
+    }
+    const data = await res.json();
+    _cache.set(url, { data, fetchedAt: Date.now() });
+    return data;
+  } catch (err) {
+    console.debug(`HF API warning: ${err.message}`);
+    return null;
+  }
+}
+
+async function fetchReadme(url) {
+  const cached = _cache.get(url);
+  if (cached && Date.now() - cached.fetchedAt < CACHE_TTL) {
+    return cached.data;
+  }
+  const now = Date.now();
+  const elapsed = now - _lastFetchTime;
+  if (elapsed < 100) {
+    await sleep(100 - elapsed);
+  }
+  _lastFetchTime = Date.now();
+  try {
+    const res = await fetch(url);
+    if (res.status === 429) {
+      const retryAfter = parseInt(res.headers.get('Retry-After') || '5', 10);
+      await sleep(retryAfter * 1000);
+      const retryRes = await fetch(url);
+      if (!retryRes.ok) return null;
+      const text = await retryRes.text();
+      _cache.set(url, { data: text, fetchedAt: Date.now() });
+      return text;
+    }
+    if (!res.ok) return null;
+    const text = await res.text();
+    _cache.set(url, { data: text, fetchedAt: Date.now() });
+    return text;
+  } catch (err) {
+    console.debug(`HF README warning: ${err.message}`);
+    return null;
+  }
+}
+
+function findClosestOrg(spoofedOrg) {
+  const lowerOrg = String(spoofedOrg).toLowerCase();
+  let best = { org: null, score: 0 };
+  for (const known of KNOWN_HF_ORGS) {
+    const score = jaroWinkler(lowerOrg, known.toLowerCase());
+    if (score >= 0.82 && score > best.score) {
+      best = { org: known, score };
+    }
+  }
+  return best;
+}
+
+function extractHFTuples(pkgJson, allFiles) {
+  const tuples = new Set();
+  let postinstallFetchFlag = false;
+
+  const scripts = pkgJson?.scripts || {};
+  let m;
+  for (const [hook, script] of Object.entries(scripts)) {
+    if (typeof script !== 'string') continue;
+
+    HF_URL_PATTERN.lastIndex = 0;
+    while ((m = HF_URL_PATTERN.exec(script)) !== null) {
+      tuples.add(`${m[1]}/${m[2]}`);
+      if (LIFECYCLE_SCRIPTS.has(hook)) {
+        postinstallFetchFlag = true;
+      }
+    }
+
+    FROM_PRETRAINED_PATTERN.lastIndex = 0;
+    while ((m = FROM_PRETRAINED_PATTERN.exec(script)) !== null) {
+      tuples.add(m[1]);
+      if (LIFECYCLE_SCRIPTS.has(hook)) {
+        postinstallFetchFlag = true;
+      }
+    }
+
+    HUB_DOWNLOAD_SINGLE.lastIndex = 0;
+    while ((m = HUB_DOWNLOAD_SINGLE.exec(script)) !== null) {
+      tuples.add(m[1]);
+      if (LIFECYCLE_SCRIPTS.has(hook)) {
+        postinstallFetchFlag = true;
+      }
+    }
+
+    HUB_DOWNLOAD_DOUBLE.lastIndex = 0;
+    while ((m = HUB_DOWNLOAD_DOUBLE.exec(script)) !== null) {
+      tuples.add(`${m[1]}/${m[2]}`);
+      if (LIFECYCLE_SCRIPTS.has(hook)) {
+        postinstallFetchFlag = true;
+      }
+    }
+  }
+
+  if (allFiles) {
+    for (const file of allFiles) {
+      if (!file.path?.match(/\.(js|ts|jsx|tsx|mjs|cjs)$/i)) continue;
+      const content = typeof file.content === 'string' ? file.content : '';
+
+      HF_URL_PATTERN.lastIndex = 0;
+      while ((m = HF_URL_PATTERN.exec(content)) !== null) {
+        tuples.add(`${m[1]}/${m[2]}`);
+      }
+
+      FROM_PRETRAINED_PATTERN.lastIndex = 0;
+      while ((m = FROM_PRETRAINED_PATTERN.exec(content)) !== null) {
+        tuples.add(m[1]);
+      }
+
+      HUB_DOWNLOAD_SINGLE.lastIndex = 0;
+      while ((m = HUB_DOWNLOAD_SINGLE.exec(content)) !== null) {
+        tuples.add(m[1]);
+      }
+
+      HUB_DOWNLOAD_DOUBLE.lastIndex = 0;
+      while ((m = HUB_DOWNLOAD_DOUBLE.exec(content)) !== null) {
+        tuples.add(`${m[1]}/${m[2]}`);
+      }
+    }
+  }
+
+  return { tuples, postinstallFetchFlag };
+}
+
+function buildHFOrgSpoofFinding(referencedRepo, org, canonicalOrg, similarityScore, postinstallFetchFlag, tags, hfMeta) {
+  const finding = {
+    id: 'HF_ORG_SPOOF',
+    severity: 'high',
+    title: 'HuggingFace org impersonation',
+    description: `Repository "${referencedRepo}" references org "${org}" which is similar to known HF org "${canonicalOrg.org}" (similarity: ${similarityScore.toFixed(3)})`,
+    evidence: JSON.stringify({
+      referencedRepo,
+      canonicalOrg: canonicalOrg.org,
+      similarityScore,
+      tags: tags || [],
+    }),
+    referencedRepo,
+    canonicalOrg: canonicalOrg.org,
+    similarityScore,
+    tags: tags || [],
+    ipiClass: 'SUPPLY_CHAIN',
+  };
+  if (hfMeta) {
+    finding.hfMeta = hfMeta;
+  }
+  return finding;
+}
+
+async function runStage2(spoofFindings, orgsToCheck, postinstallFetchFlag) {
+  const newFindings = [];
+
+  for (const [referencedRepo, { org, canonicalOrg, similarityScore, finding }] of orgsToCheck) {
+    const tags = [];
+    let hfMeta = null;
+
+    const modelUrl = `${API_BASE}/api/models/${referencedRepo}`;
+    const canonicalUrl = canonicalOrg.org !== org ? `${API_BASE}/api/models/${canonicalOrg.org}/${referencedRepo.split('/')[1]}` : null;
+    const userUrl = `${API_BASE}/api/users/${org}`;
+
+    const spoofedModel = await fetchWithCache(modelUrl);
+    const canonicalModel = canonicalUrl ? await fetchWithCache(canonicalUrl) : null;
+    const userData = await fetchWithCache(userUrl);
+
+    // Org age check for NEW_ORG tag
+    if (userData?.dateCreated) {
+      const created = new Date(userData.dateCreated);
+      const ageDays = (Date.now() - created.getTime()) / (1000 * 60 * 60 * 24);
+      hfMeta = {
+        orgAgeDays: Math.round(ageDays),
+        repoDownloads: spoofedModel?.downloads ?? 0,
+      };
+      if (ageDays < 30) {
+        tags.push('NEW_ORG');
+      }
+    }
+
+    // README clone check
+    if (canonicalOrg.org !== org) {
+      const readmeSpoof = await fetchReadme(`${API_BASE}/${referencedRepo}/resolve/main/README.md`);
+      const readmeCanonical = await fetchReadme(`${API_BASE}/${canonicalOrg.org}/${referencedRepo.split('/')[1]}/resolve/main/README.md`);
+
+      if (readmeSpoof && readmeCanonical) {
+        const fp1 = simhash(readmeSpoof);
+        const fp2 = simhash(readmeCanonical);
+        const simScore = simhashSimilarity(fp1, fp2);
+
+        if (simScore >= 0.9) {
+          const readmeFinding = {
+            id: 'HF_README_CLONE',
+            severity: 'high',
+            title: 'HuggingFace README clone',
+            description: `README of "${referencedRepo}" is highly similar (${(simScore * 100).toFixed(1)}%) to canonical org "${canonicalOrg.org}/${referencedRepo.split('/')[1]}"`,
+            evidence: JSON.stringify({
+              referencedRepo,
+              canonicalOrg: canonicalOrg.org,
+              similarityScore: simScore,
+              tags: [],
+            }),
+            referencedRepo,
+            canonicalOrg: canonicalOrg.org,
+            similarityScore: simScore,
+            tags: [],
+            ipiClass: 'SUPPLY_CHAIN',
+          };
+          if (hfMeta) readmeFinding.hfMeta = hfMeta;
+          newFindings.push(readmeFinding);
+        }
+      }
+    }
+
+    // Artifact mismatch check
+    if (spoofedModel?.cardData?.library_name && spoofedModel?.siblings) {
+      const libName = spoofedModel.cardData.library_name;
+      if (HF_ARTIFACT_LIBS.has(libName)) {
+        for (const sibling of spoofedModel.siblings) {
+          const fn = sibling.rfilename || '';
+          if (SUSPICIOUS_EXTENSIONS.test(fn)) {
+            const artifactFinding = {
+              id: 'HF_ARTIFACT_MISMATCH',
+              severity: 'critical',
+              title: 'HF artifact mismatch — suspicious binary in model repo',
+              description: `Model "${referencedRepo}" declares library "${libName}" but contains suspicious file "${fn}"`,
+              evidence: JSON.stringify({
+                referencedRepo,
+                artifactConflict: { declaredType: libName, suspiciousFilename: fn },
+                tags: [],
+              }),
+              referencedRepo,
+              artifactConflict: { declaredType: libName, suspiciousFilename: fn },
+              tags: [],
+              ipiClass: 'SUPPLY_CHAIN',
+            };
+            if (hfMeta) artifactFinding.hfMeta = hfMeta;
+            newFindings.push(artifactFinding);
+            break;
+          }
+        }
+      }
+    }
+
+    // Apply NEW_ORG and POSTINSTALL_FETCH tags to all findings for this repo
+    const repoSpoofFindings = spoofFindings.filter(f => f.referencedRepo === referencedRepo);
+    for (const sf of repoSpoofFindings) {
+      if (tags.length > 0) {
+        if (!sf.tags) sf.tags = [];
+        for (const t of tags) {
+          if (!sf.tags.includes(t)) sf.tags.push(t);
+        }
+      }
+      if (hfMeta) {
+        sf.hfMeta = hfMeta;
+      }
+    }
+    for (const nf of newFindings) {
+      if (nf.referencedRepo === referencedRepo) {
+        if (tags.length > 0) {
+          if (!nf.tags) nf.tags = [];
+          for (const t of tags) {
+            if (!nf.tags.includes(t)) nf.tags.push(t);
+          }
+        }
+      }
+    }
+  }
+
+  // POSTINSTALL_FETCH escalation
+  if (postinstallFetchFlag) {
+    const allStage2Findings = [...spoofFindings, ...newFindings];
+    const escalatedRepos = new Set();
+    for (const f of allStage2Findings) {
+      if (f.referencedRepo) escalatedRepos.add(f.referencedRepo);
+    }
+    for (const f of allStage2Findings) {
+      if (escalatedRepos.has(f.referencedRepo)) {
+        if (severityIndex(f.severity) < severityIndex('critical')) {
+          f.severity = 'critical';
+        }
+        if (!f.tags) f.tags = [];
+        if (!f.tags.includes('POSTINSTALL_ESCALATED')) {
+          f.tags.push('POSTINSTALL_ESCALATED');
+        }
+      }
+    }
+  }
+
+  return newFindings;
+}
+
+export async function scan(pkgJson, files = [], registryMeta = null, allFiles = null) {
+  const { tuples, postinstallFetchFlag } = extractHFTuples(pkgJson, allFiles || files);
+
+  if (tuples.size === 0) return [];
+
+  // Stage 1: org spoof detection (local only)
+  const spoofFindings = [];
+  const orgsToCheck = []; // [referencedRepo, { org, canonicalOrg, similarityScore, finding }]
+
+  for (const tuple of tuples) {
+    const parts = tuple.split('/');
+    if (parts.length < 2) continue;
+    const org = parts[0];
+
+    const canonicalOrg = findClosestOrg(org);
+    if (!canonicalOrg.org) continue;
+    if (org.toLowerCase() === canonicalOrg.org.toLowerCase()) continue;
+
+    const finding = buildHFOrgSpoofFinding(tuple, org, canonicalOrg, canonicalOrg.score, postinstallFetchFlag, []);
+    spoofFindings.push(finding);
+    orgsToCheck.push([tuple, { org, canonicalOrg, similarityScore: canonicalOrg.score, finding }]);
+  }
+
+  if (spoofFindings.length === 0) return [];
+
+  // Stage 2: network checks
+  const stage2Findings = await runStage2(spoofFindings, orgsToCheck, postinstallFetchFlag);
+
+  // Deduplicate POSTINSTALL_ESCALATED tag in evidence
+  for (const f of [...spoofFindings, ...stage2Findings]) {
+    if (f.tags && f.tags.length > 0) {
+      try {
+        const ev = JSON.parse(f.evidence);
+        ev.tags = [...f.tags];
+        f.evidence = JSON.stringify(ev);
+      } catch {
+        // evidence wasn't JSON, leave as-is
+      }
+    }
+  }
+
+  return [...spoofFindings, ...stage2Findings];
+}
+
+export function clearCache() {
+  _cache.clear();
+  _lastFetchTime = 0;
+}
+
+export { KNOWN_HF_ORGS, jaroWinkler, simhash, simhashSimilarity };

package/backend/detectors/hf-impersonation/jaro-winkler.js

@@ -0,0 +1,44 @@
+export function jaroWinkler(s1, s2) {
+  if (s1 === s2) return 1;
+  const len1 = s1.length, len2 = s2.length;
+  if (len1 === 0 || len2 === 0) return 0;
+
+  const matchDist = Math.floor(Math.max(len1, len2) / 2) - 1;
+  const matches1 = new Array(len1).fill(false);
+  const matches2 = new Array(len2).fill(false);
+  let matches = 0;
+
+  for (let i = 0; i < len1; i++) {
+    const start = Math.max(0, i - matchDist);
+    const end = Math.min(len2, i + matchDist + 1);
+    for (let j = start; j < end; j++) {
+      if (matches2[j]) continue;
+      if (s1[i] !== s2[j]) continue;
+      matches1[i] = true;
+      matches2[j] = true;
+      matches++;
+      break;
+    }
+  }
+
+  if (matches === 0) return 0;
+
+  let transpositions = 0, k = 0;
+  for (let i = 0; i < len1; i++) {
+    if (!matches1[i]) continue;
+    while (!matches2[k]) k++;
+    if (s1[i] !== s2[k]) transpositions++;
+    k++;
+  }
+
+  const jaro = (matches / len1 + matches / len2 + (matches - transpositions / 2) / matches) / 3;
+
+  let prefix = 0;
+  const maxPrefix = Math.min(4, len1, len2);
+  for (let i = 0; i < maxPrefix; i++) {
+    if (s1[i] === s2[i]) prefix++;
+    else break;
+  }
+
+  return jaro + prefix * 0.1 * (1 - jaro);
+}

package/backend/detectors/hf-impersonation/known-orgs.js

@@ -0,0 +1,5 @@
+export const KNOWN_HF_ORGS = [
+  'openai', 'meta-llama', 'mistralai', 'google', 'microsoft',
+  'stabilityai', 'EleutherAI', 'huggingface', 'tiiuae', 'cohere',
+  'anthropic', 'deepseek-ai', 'Qwen', 'NousResearch', 'teknium',
+];

package/backend/detectors/hf-impersonation/simhash.js

@@ -0,0 +1,46 @@
+function hashToken(str) {
+  let hash = 5381;
+  for (let i = 0; i < str.length; i++) {
+    hash = ((hash << 5) + hash) + str.charCodeAt(i);
+    hash = hash & hash;
+  }
+  return hash >>> 0;
+}
+
+export function simhash(text) {
+  const v = new Array(64).fill(0);
+  const tokens = text.toLowerCase().split(/\s+/).filter(Boolean);
+
+  for (const token of tokens) {
+    const h = hashToken(token);
+    for (let i = 0; i < 64; i++) {
+      if ((h >> i) & 1) {
+        v[i] += 1;
+      } else {
+        v[i] -= 1;
+      }
+    }
+  }
+
+  let fingerprint = 0n;
+  for (let i = 0; i < 64; i++) {
+    if (v[i] > 0) {
+      fingerprint |= (1n << BigInt(i));
+    }
+  }
+  return fingerprint;
+}
+
+export function hammingDistance(a, b) {
+  let xor = a ^ b;
+  let count = 0;
+  while (xor > 0n) {
+    count += Number(xor & 1n);
+    xor >>= 1n;
+  }
+  return count;
+}
+
+export function similarity(a, b) {
+  return 1 - hammingDistance(a, b) / 64;
+}

package/backend/detectors/index.js

@@ -9,8 +9,10 @@ import * as atk008 from './atk-008-tarball-tamper.js';
 import * as atk009 from './atk-009-dormant-trigger.js';
 import * as atk010 from './atk-010-sandbox-evasion.js';
 import * as atk011 from './atk-011-transitive-prop.js';
+import { scanAll as megalodonScan } from './megalodon/index.js';
+import { scan as hfScan } from './hf-impersonation/index.js';
 
-export async function runAll(pkgJson, files = []) {
+export async function runAll(pkgJson, files = [], registryMeta = null, allFiles = null) {
   const findings = [];
   findings.push(...await atk001.scan(pkgJson, files));
   findings.push(...await atk002.scan(pkgJson, files));
@@ -23,5 +25,7 @@ export async function runAll(pkgJson, files = []) {
   findings.push(...await atk009.scan(pkgJson, files));
   findings.push(...await atk010.scan(pkgJson, files));
   findings.push(...await atk011.scan(pkgJson, files));
+  findings.push(...await megalodonScan(pkgJson, allFiles || files, registryMeta));
+  findings.push(...await hfScan(pkgJson, files, registryMeta, allFiles || files));
   return findings.sort((a, b) => b.severity.localeCompare(a.severity));
 }

package/backend/detectors/megalodon/d1-workflow-scan.js

@@ -0,0 +1,147 @@
+import { MegalodonSignal } from './types.js';
+import yaml from 'js-yaml';
+
+const C2_EXFIL_RE = /curl\s+.*?https?:\/\/(?!github\.com|githubusercontent\.com|raw\.githubusercontent\.com)[^\s'"]+/i;
+const SECRETS_REF_RE = /\$\{\{?\s*secrets\.\w+/;
+const B64_DECODE_CHAIN_RE = /base64\s+-d\s*[|>]\s*(ba)?sh/;
+
+function isWorkflowFile(f) {
+  const p = f.path.replace(/\\/g, '/');
+  return /\.github\/workflows\/.+\.(yml|yaml)$/i.test(p);
+}
+
+function countExecutableLines(text) {
+  return text.split('\n').filter(l => l.trim() && !l.trim().startsWith('#')).length;
+}
+
+function extractRunBlocks(parsed) {
+  const runs = [];
+  if (!parsed || typeof parsed !== 'object') return runs;
+
+  const walk = (obj) => {
+    if (!obj || typeof obj !== 'object') return;
+    if (Array.isArray(obj)) { obj.forEach(walk); return; }
+    for (const [k, v] of Object.entries(obj)) {
+      if (k === 'run' && typeof v === 'string') {
+        runs.push(v);
+      }
+      if (k === 'env' && typeof v === 'object' && v !== null) {
+        runs.push({ _env: v });
+      }
+      walk(v);
+    }
+  };
+  walk(parsed);
+  return runs;
+}
+
+function extractRunBlocksRaw(text) {
+  const runs = [];
+  const runMatch = text.match(/run:\s*[|>]\s*\n(\s{2,}.*(?:\n\s{2,}.*)*)/g);
+  if (runMatch) runs.push(...runMatch.map(m => m.replace(/^run:\s*[|>]\s*\n/, '')));
+
+  const inlineRe = /run:\s*['"](.+?)['"]\s*$/gm;
+  let m;
+  while ((m = inlineRe.exec(text)) !== null) runs.push(m[1]);
+
+  const envRe = /env:\s*\n((?:\s{2,}\w+:\s*.+\n?)*)/g;
+  let em;
+  while ((em = envRe.exec(text)) !== null) runs.push({ _env: em[1] });
+  return runs;
+}
+
+function runInStepHasBoth(step, signal) {
+  const runVal = step.run;
+  const envVals = step.env ? Object.values(step.env).filter(v => typeof v === 'string').join(' ') : '';
+  const combined = typeof runVal === 'string' ? `${runVal} ${envVals}` : '';
+
+  if (signal === 'exfil') {
+    return C2_EXFIL_RE.test(combined) && SECRETS_REF_RE.test(combined);
+  }
+  if (signal === 'decode') {
+    return B64_DECODE_CHAIN_RE.test(combined);
+  }
+  return false;
+}
+
+export async function scan(allFiles) {
+  const evidence = [];
+  const workflowFiles = allFiles.filter(isWorkflowFile);
+
+  for (const f of workflowFiles) {
+    if (f.content.length > 512 * 1024) continue;
+
+    let parsed = null;
+    let parseError = null;
+    try {
+      parsed = yaml.load(f.content);
+    } catch (e) {
+      parseError = e;
+    }
+
+    const rawRunBlocks = parsed ? extractRunBlocks(parsed) : extractRunBlocksRaw(f.content);
+    const runStrings = rawRunBlocks.filter(r => typeof r === 'string');
+    const envBlocks = rawRunBlocks.filter(r => typeof r === 'object' && r._env);
+
+    let exfilTriggered = false;
+    let decodeTriggered = false;
+
+    for (const runStr of runStrings) {
+      if (!exfilTriggered && C2_EXFIL_RE.test(runStr) && SECRETS_REF_RE.test(runStr)) {
+        exfilTriggered = true;
+        evidence.push({
+          signal: MegalodonSignal.WORKFLOW_C2_EXFIL,
+          file: f.path,
+          excerpt: runStr.slice(0, 120),
+          detail: 'C2 outbound call co-occurs with credentials reference in run block',
+        });
+      }
+
+      if (!decodeTriggered && B64_DECODE_CHAIN_RE.test(runStr)) {
+        decodeTriggered = true;
+        evidence.push({
+          signal: MegalodonSignal.WORKFLOW_DECODE_CHAIN,
+          file: f.path,
+          excerpt: runStr.slice(0, 120),
+          detail: 'Base64 decode pipe to shell — obfuscated payload execution',
+        });
+      }
+    }
+
+    if (parsed && typeof parsed === 'object' && !Array.isArray(parsed)) {
+      const steps = parsed.jobs ? Object.values(parsed.jobs).flatMap(j => j.steps || []) : [];
+      for (const step of steps) {
+        if (!exfilTriggered && runInStepHasBoth(step, 'exfil')) {
+          exfilTriggered = true;
+          const runVal = step.run || '';
+          evidence.push({
+            signal: MegalodonSignal.WORKFLOW_C2_EXFIL,
+            file: f.path,
+            excerpt: runVal.slice(0, 120),
+            detail: 'C2 outbound call co-occurs with secrets reference in same step',
+          });
+        }
+        if (!decodeTriggered && runInStepHasBoth(step, 'decode')) {
+          decodeTriggered = true;
+          const runVal = step.run || '';
+          evidence.push({
+            signal: MegalodonSignal.WORKFLOW_DECODE_CHAIN,
+            file: f.path,
+            excerpt: runVal.slice(0, 120),
+            detail: 'Base64 decode pipe to shell — obfuscated payload execution',
+          });
+        }
+      }
+    }
+
+    const lineCount = countExecutableLines(f.content);
+    if ((exfilTriggered || decodeTriggered) && lineCount >= 100 && lineCount <= 120) {
+      const found = evidence.find(e => e.signal === MegalodonSignal.WORKFLOW_C2_EXFIL || e.signal === MegalodonSignal.WORKFLOW_DECODE_CHAIN);
+      if (found) {
+        found.detail += ` | Matches ${lineCount}-line Megalodon payload footprint`;
+      }
+    }
+  }
+
+  return evidence;
+}