{
 "public_id": "AIR-2026-0139",
 "incident_id": "2026-06-unit42-clawhub-malicious-skills",
 "date_disclosed": "2026-06-23",
 "date_occurred": "2026-02",
 "title": "Five malicious OpenClaw skills on ClawHub: macOS infostealers, scanner evasion, affiliate injection and crypto front-running",
 "class": "in_the_wild",
 "attack_surface": "skill_plugin",
 "initial_vector": "malicious_marketplace_package",
 "agent_capability_abused": [
  "skill_execution",
  "agent_identity",
  "financial_recommendation",
  "shell_execution",
  "file_read",
  "autonomous_purchasing"
 ],
 "target_product": "OpenClaw / ClawHub skill marketplace",
 "target_vendor": "OpenClaw",
 "autonomy_level": "semi_autonomous",
 "impact_realized": false,
 "impact_type": [
  "credential_theft",
  "malware_installation",
  "financial_manipulation",
  "financial_fraud",
  "unauthorized_action"
 ],
 "blast_radius": "Users who installed the five skills before takedown (Feb-May 2026)",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI04",
   "ASI05",
   "ASI06"
  ],
  "mitre_atlas": [],
  "labels": [
   "supply_chain",
   "malicious_skill",
   "infostealer",
   "skill_marketplace",
   "scanner_evasion",
   "size_padding",
   "affiliate_injection",
   "front_running"
  ]
 },
 "defense_present": "ClawHub screening via VirusTotal and ClawScan",
 "defense_bypassed": true,
 "fix_shipped": "Skills removed from ClawHub",
 "primary_sources": [
  "https://unit42.paloaltonetworks.com/openclaw-ai-supply-chain-risk/"
 ],
 "verified_quote": "The lack of isolation between skill logic and agent authority means that installation results in complete control over the agent's identity.",
 "confidence": "high",
 "notes": "Named skills: cluw and an AMOS variant (macOS infostealers), omnicogg (22 MB README.md padding to evade scanners), money-radar (runtime affiliate injection), letssendit (agentic crypto front-running / pump-and-dump). Authors Bellary Seetharam, Mohamed, Melicher, Starov. No published victim count, so impact_realized left false. Also reported as: 'Unit 42 finds five malicious ClawHub skills that evaded VirusTotal and ClawScan, including 22 MB padding evasion and runtime affiliate injection'.",
 "is_umbrella": true,
 "umbrella_constituents": [],
 "umbrella_reason": "Campaign roundup of five named skills; no individual skill is separately cataloged.",
 "risk_category": "security_fraud",
 "risk_secondary": [],
 "risk_subcategory": "Supply Chain Compromise",
 "risk_sub_secondary": [
  "Credential & Secret Theft",
  "Unauthorized financial commitment"
 ],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": false,
 "agency_reason": "the agents executed the malicious skills' payloads",
 "vector_family": "malicious_component",
 "vector_detail": "malicious_marketplace_package",
 "guardrail_kind": [
  "unknown"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI04",
 "agent_framework": "unknown",
 "model_provider": "unknown",
 "model_name": "",
 "detection_mechanism": "threat_intel",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "supply_chain_vulnerabilities",
 "eai_domain": "tool_misuse",
 "eai_secondary": [
  "unsafe_actuation",
  "credential_theft"
 ],
 "eai_reason": "subcategory: Supply Chain Compromise",
 "asi_curated": [
  "ASI04",
  "ASI05",
  "ASI06"
 ],
 "asi_scope": "in_scope",
 "asi_provenance": "curated",
 "asi_reason": "curated: ASI04,ASI05,ASI06",
 "submitted_by": "EAI Internal"
}