{
 "public_id": "AIR-2026-0236",
 "incident_id": "2026-09-anthropic-gtg-50029-hacktivist-fafsearch",
 "date_disclosed": "2026-09-10",
 "date_occurred": null,
 "title": "GTG-50029: a single French-speaking hacktivist used Claude with sub-agents to breach European political entities and build 'fafsearch', a mass doxxing platform",
 "class": "in_the_wild",
 "attack_surface": "agent_framework",
 "initial_vector": "exposed_api_keys_and_wordpress_reinstall_race_condition_exploit",
 "agent_capability_abused": [
  "autonomous_exploitation",
  "sub_agent_orchestration",
  "exploit_development",
  "webshell_deployment",
  "data_exfiltration",
  "doxxing_platform_engineering"
 ],
 "target_product": "Claude",
 "target_vendor": "Anthropic",
 "autonomy_level": "fully_autonomous",
 "impact_realized": true,
 "impact_type": [
  "unauthorized_access",
  "data_exfiltration",
  "doxxing",
  "privacy_violation"
 ],
 "blast_radius": "42 tracked target entities (European political parties, media, think tanks and their SaaS providers), internal access to at least 14; ~140,000 records including political opinions exfiltrated from one platform; an estimated 12-26 GB of database dumps (donor/member records, a 15,000-message mailbox, minors' data); a doxxing search engine loaded with tens of millions of rows published on Tor",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI03"
  ],
  "mitre_atlas": [],
  "labels": [
   "hacktivist",
   "doxxing",
   "agentic_offense",
   "sub_agents",
   "privacy_mass_attack"
  ]
 },
 "defense_present": "Anthropic Usage Policy safeguards and misuse detection",
 "defense_bypassed": true,
 "fix_shipped": "Anthropic investigated and disrupted the campaign, banning associated accounts (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": "Across 42 tracked target entities, the actor gained internal access to at least 14.",
 "confidence": "high",
 "notes": "Anthropic September 2026 report (PDF). Signature technique an undocumented WordPress re-installation race condition creating a rogue admin account, developed and debugged with Claude in-session; the actor also poisoned victim backups for persistence. Anthropic calls fafsearch 'one of the clearest cases we have seen of AI-assisted software engineering applied directly to a mass attack on privacy—and the entire platform was created by just one person.'",
 "risk_category": "security_fraud",
 "risk_secondary": [
  "privacy"
 ],
 "risk_subcategory": "Credential & Secret Theft",
 "risk_sub_secondary": [
  "Unauthorized Access & Account Takeover"
 ],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": true,
 "agency_reason": "sub-agent framework executed exploitation and harvesting; the doxxing platform was human-directed",
 "vector_family": "conventional_vulnerability",
 "vector_detail": "exposed_api_keys_and_wordpress_reinstall_race_condition_exploit",
 "guardrail_kind": [
  "abuse_detection"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI03",
 "agent_framework": "unknown",
 "model_provider": "anthropic",
 "model_name": "",
 "detection_mechanism": "vendor_disclosure",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "credential_theft",
 "eai_domain": "access_control_and_permissions",
 "eai_secondary": [
  "privilege_escalation",
  "data_exfiltration_channels",
  "sensitive_data_exposure"
 ],
 "eai_reason": "subcategory: Credential & Secret Theft",
 "asi_curated": [],
 "asi_scope": "in_scope",
 "asi_provenance": "rule",
 "asi_reason": "ASI03 (eai_category=credential_theft)",
 "submitted_by": "EAI Internal"
}