{
 "public_id": "AIR-2025-0143",
 "incident_id": "2025-10-openai-russian-malware-tooling",
 "date_disclosed": "2025-10-07",
 "date_occurred": "2025",
 "title": "OpenAI banned Russian-speaking criminal accounts building RAT, stealer and crypter components with ChatGPT",
 "class": "in_the_wild",
 "attack_surface": "consumer_chatbot",
 "initial_vector": "direct_misuse_for_malware_component_development",
 "agent_capability_abused": [
  "code_generation",
  "debugging",
  "evasion_technique_design"
 ],
 "target_product": "ChatGPT",
 "target_vendor": "OpenAI",
 "autonomy_level": "assistant",
 "impact_realized": true,
 "impact_type": [
  "malware_development",
  "credential_theft_tooling"
 ],
 "blast_radius": "Multiple accounts tied to a Telegram-advertised criminal group; tooling for in-memory loaders, UAC/SmartScreen/MOTW bypasses, browser cookie decryption, wallet parsing and clipboard hijacking",
 "cve": [],
 "taxonomy": {
  "owasp_asi": [
   "ASI04",
   "ASI02"
  ],
  "mitre_atlas": [],
  "labels": [
   "capability_uplift",
   "building_block_evasion",
   "account_hopping"
  ]
 },
 "defense_present": "Model refusals for overtly malicious requests",
 "defense_bypassed": true,
 "fix_shipped": "Accounts banned (Oct 2025)",
 "primary_sources": [
  "https://cdn.openai.com/threat-intelligence-reports/7d662b68-952f-4dfd-a2f2-fe55b041cc4a/disrupting-malicious-uses-of-ai-october-2025.pdf"
 ],
 "verified_quote": "We banned ChatGPT accounts that were attempting to use the model to help develop and refine malware, including a remote‑access trojan, credential stealers, and features to evade detection.",
 "confidence": "high",
 "notes": "Non-agentic in the strict sense - OpenAI states 'Our models were not used to execute any threat actor tooling and workflows' - but included because the outputs were assembled into deployed malware. The tradecraft of interest is decomposition: the actor elicited individually innocuous building blocks after direct requests were refused, and rotated one conversation per account to evade behavioural detection.",
 "risk_category": "security_fraud",
 "risk_secondary": [
  "product_misuse"
 ],
 "risk_subcategory": "Supply Chain Compromise",
 "risk_sub_secondary": [
  "Credential & Secret Theft"
 ],
 "ai_entity": "generative",
 "agency": "human_acted_on_output",
 "agency_debatable": false,
 "agency_reason": "ChatGPT wrote malware components that humans compiled and used",
 "vector_family": "misuse",
 "vector_detail": "direct_misuse_for_malware_component_development",
 "guardrail_kind": [
  "unknown"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI04",
 "agent_framework": "unknown",
 "model_provider": "openai",
 "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",
  "policy_drift"
 ],
 "eai_reason": "subcategory: Supply Chain Compromise",
 "asi_curated": [],
 "asi_scope": "in_scope",
 "asi_provenance": "rule",
 "asi_reason": "ASI04 (eai_category=supply_chain_vulnerabilities); ASI02 (impact=tool_misuse)",
 "submitted_by": "EAI Internal"
}