{
 "public_id": "AIR-2026-0233",
 "incident_id": "2026-09-anthropic-gtg-20006-russian-espionage",
 "date_disclosed": "2026-09-10",
 "date_occurred": null,
 "title": "GTG-20006: Russian state-nexus espionage actor (Midnight Blizzard-aligned) used Claude agents to automate a multi-victim intrusion campaign, including autonomous malware rebuild-on-detection",
 "class": "in_the_wild",
 "attack_surface": "agent_framework",
 "initial_vector": "device_code_phishing_and_ai_driven_intrusion_workflows",
 "agent_capability_abused": [
  "autonomous_task_orchestration",
  "code_execution",
  "malware_rebuild_on_detection",
  "credential_harvesting",
  "data_exfiltration",
  "phishing_infrastructure_automation"
 ],
 "target_product": "Claude / Claude Code",
 "target_vendor": "Anthropic",
 "autonomy_level": "semi_autonomous",
 "impact_realized": true,
 "impact_type": [
  "unauthorized_access",
  "data_exfiltration",
  "espionage",
  "credential_theft"
 ],
 "blast_radius": "more than 20 organizations targeted (government ministries, defense/intelligence bodies, embassies, think tanks, drone supply chain), concentrated in Ukraine and Europe; mail records exfiltrated from at least eight organizations; a North African government credential database of more than 300,000 national identity records stolen",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI04",
   "ASI05",
   "ASI03"
  ],
  "mitre_atlas": [],
  "labels": [
   "state_sponsored",
   "agentic_offense",
   "malware_evasion_loop",
   "midnight_blizzard",
   "device_code_phishing"
  ]
 },
 "defense_present": "Anthropic Usage Policy safeguards and misuse detection",
 "defense_bypassed": true,
 "fix_shipped": "Anthropic banned associated accounts, strengthened safeguards and shared intelligence with authorities and partners (September 2026)",
 "primary_sources": [
  "https://www-cdn.anthropic.com/e50be2e51e7695dc4b1366a37a245a597377d3b5/Anthropic-Detecting-and-countering-091026.pdf",
  "https://www.anthropic.com/threat-intelligence-report-september-2026"
 ],
 "verified_quote": "If their monitoring AI agents identified that any of their deployed malware was detected by a security product, agents would then set about the process of autonomously modifying and rebuilding the malware to evade the existing detections.",
 "confidence": "high",
 "notes": "From Anthropic's 'Detecting and countering misuse of AI: September 2026' report (PDF is the primary source of record; web landing page also cited). Attribution 'consistent with public reporting linking the actor to Midnight Blizzard'; operator handle 'JackPoterz'. Used AI across recon, initial access (device-code phishing via the actor's 'Embassy Kit' framework), collection/exfiltration and persistence; also compromised at least three hotel-WiFi hospitality vendors (technique Microsoft calls CaptiveCrunch) and took over WhatsApp accounts of two former high-level Ukrainian officials. Coded semi_autonomous per the report's own placement of GTG-20006 ('a human making each individual targeting decision'), though scheduled token-renewal/collection jobs ran with no human in the loop.",
 "risk_category": "security_fraud",
 "risk_secondary": [
  "privacy",
  "product_misuse"
 ],
 "risk_subcategory": "Supply Chain Compromise",
 "risk_sub_secondary": [
  "Credential & Secret Theft",
  "Remote Code Execution & Sandbox Escape",
  "Unauthorized Access & Account Takeover"
 ],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": false,
 "agency_reason": "Claude agents automated reconnaissance, exploitation, exfiltration and rebuilt malware on detection within the actor's workflow",
 "vector_family": "other",
 "vector_detail": "device_code_phishing_and_ai_driven_intrusion_workflows",
 "guardrail_kind": [
  "abuse_detection"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI04",
 "agent_framework": "claude_code",
 "model_provider": "anthropic",
 "model_name": "",
 "detection_mechanism": "vendor_disclosure",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "supply_chain_vulnerabilities",
 "eai_domain": "tool_misuse",
 "eai_secondary": [
  "credential_theft",
  "privilege_escalation",
  "data_exfiltration_channels"
 ],
 "eai_reason": "subcategory: Supply Chain Compromise",
 "asi_curated": [],
 "asi_scope": "in_scope",
 "asi_provenance": "rule",
 "asi_reason": "ASI04 (eai_category=supply_chain_vulnerabilities); ASI05 (vector=code_exec); ASI03 (signal=identity)",
 "submitted_by": "EAI Internal"
}