{
 "public_id": "AIR-2026-0177",
 "incident_id": "2026-08-microsoft-skill-scanner-bypass-1m-skills",
 "date_disclosed": "2026-08",
 "date_occurred": null,
 "title": "Microsoft's Copilot Cowork Skill security scanner misses 89% of malicious Skills, and 99.6% after one obfuscation step",
 "class": "research_demo",
 "attack_surface": "skill_plugin",
 "initial_vector": "malicious_skill",
 "agent_capability_abused": [
  "skill_marketplace_ingestion",
  "llm_based_security_scanning"
 ],
 "target_product": "Microsoft Copilot Cowork built-in Skill security scan",
 "target_vendor": "Microsoft",
 "autonomy_level": "semi_autonomous",
 "impact_realized": false,
 "impact_type": [
  "defense_evasion"
 ],
 "blast_radius": "every org relying on Microsoft's Skill scan to vet Copilot Cowork Skills",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI05",
   "ASI04"
  ],
  "mitre_atlas": [],
  "labels": [
   "scanner_evasion",
   "supply_chain",
   "keyword_matching_defense",
   "llm_judging_llm"
  ]
 },
 "defense_present": "Microsoft's built-in Skill security scanner",
 "defense_bypassed": true,
 "fix_shipped": "none stated",
 "primary_sources": [
  "https://www.promptarmor.com/resources/microsoft-scan-misses-1-million-malicious-skills"
 ],
 "verified_quote": "We seeded 1,046,565 unique Skills across six marketplaces with malicious content from Microsoft's own BIPIA benchmark and ran Microsoft's Skill security scan.",
 "confidence": "high",
 "notes": "PROVENANCE CAVEAT: the page carries no publication date; 2026-08 in the incident_id is provisional and date_disclosed is left null. PromptArmor. Detection rate ~11% baseline, 0.4% after splitting flagged keywords. Compare 2026-05-gecko-skill-scanner-test-file-bypass and 2026-07-skillcloak-scanner-evasion for the same defense-evasion theme against other scanners. | date_disclosed is recorded to the month only; no source establishes the exact day.",
 "risk_category": "security_fraud",
 "risk_secondary": [],
 "risk_subcategory": "Supply Chain Compromise",
 "risk_sub_secondary": [],
 "ai_entity": "generative",
 "agency": "ai_as_target",
 "agency_debatable": true,
 "agency_reason": "the defender's LLM-based Skill scanner is the thing being defeated",
 "vector_family": "malicious_component",
 "vector_detail": "malicious_skill",
 "guardrail_kind": [
  "unknown"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI05",
 "agent_framework": "unknown",
 "model_provider": "microsoft",
 "model_name": "",
 "detection_mechanism": "external_researcher",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "supply_chain_vulnerabilities",
 "eai_domain": "tool_misuse",
 "eai_secondary": [
  "policy_drift"
 ],
 "eai_reason": "subcategory: Supply Chain Compromise",
 "asi_curated": [
  "ASI05"
 ],
 "asi_scope": "in_scope",
 "asi_provenance": "curated_plus_rule",
 "asi_reason": "curated: ASI05 | added ASI04 (vector_family=malicious_component)",
 "submitted_by": "EAI Internal"
}