{
 "public_id": "AIR-2025-0028",
 "incident_id": "2025-04-anthropic-claude-misuse-report-march",
 "date_disclosed": "2025-04-23",
 "date_occurred": "2025-03",
 "title": "Anthropic disclosed Claude misuse for an influence-as-a-service bot network, credential stuffing against cameras, recruitment fraud and novice malware development",
 "class": "in_the_wild",
 "attack_surface": "other",
 "initial_vector": "policy_violating_use",
 "agent_capability_abused": [
  "content_generation",
  "persona_orchestration",
  "credential_testing",
  "code_generation"
 ],
 "target_product": "Claude",
 "target_vendor": "Anthropic",
 "autonomy_level": "semi_autonomous",
 "impact_realized": true,
 "impact_type": [
  "ecosystem_abuse",
  "credential_theft",
  "financial_loss"
 ],
 "blast_radius": "over 100 orchestrated social media bot personas; leaked credentials tested against internet-facing security cameras; recruitment fraud targeting Eastern Europe",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI10",
   "ASI03"
  ],
  "mitre_atlas": [],
  "labels": [
   "influence_as_a_service",
   "persona_orchestration",
   "capability_uplift",
   "vendor_disclosure",
   "account_enforcement"
  ]
 },
 "defense_present": "Anthropic usage policy enforcement and misuse detection",
 "defense_bypassed": true,
 "fix_shipped": "accounts banned; detection learnings folded into safeguards",
 "primary_sources": [
  "https://blog.securitybreak.io/why-prompts-are-the-new-iocs-you-didnt-see-coming-46ecaacafe0a",
  "https://incidentdatabase.ai/cite/1054"
 ],
 "verified_quote": "This report outlines several case studies on how actors have misused our models, as well as the steps we have taken to detect and counter such misuse.",
 "confidence": "high",
 "notes": "The influence-as-a-service case is the one that matters for this corpus: Claude was not writing posts on demand, it was the orchestration layer deciding which of 100+ personas engaged with what and when. That is an agent running a campaign, not a tool producing text. Anthropic could not confirm downstream deployment of the malware case, so impact_realized rests on the bot network and credential testing. AI Incident Database incident 1054.",
 "risk_category": "security_fraud",
 "risk_secondary": [],
 "risk_subcategory": "Credential & Secret Theft",
 "risk_sub_secondary": [],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": true,
 "agency_reason": "Claude orchestrated the bot network and tested credentials",
 "vector_family": "misuse",
 "vector_detail": "policy_violating_use",
 "guardrail_kind": [
  "abuse_detection"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [
   1054
  ],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI10",
 "agent_framework": "unknown",
 "model_provider": "anthropic",
 "model_name": "",
 "detection_mechanism": "unknown",
 "tool_access": "unknown",
 "financial_loss_band": "unknown",
 "eai_category": "credential_theft",
 "eai_domain": "access_control_and_permissions",
 "eai_secondary": [
  "unsafe_actuation"
 ],
 "eai_reason": "subcategory: Credential & Secret Theft",
 "asi_curated": [],
 "asi_scope": "in_scope",
 "asi_provenance": "rule",
 "asi_reason": "ASI10 (adversary-operated agent (vector_family=misuse)); ASI03 (eai_category=credential_theft)",
 "submitted_by": "EAI Internal"
}