{
 "public_id": "AIR-2026-0280",
 "incident_id": "2026-10-openai-unauthorized-sepolia-wallet-deployment",
 "date_disclosed": "2026-10-15",
 "date_occurred": "2026-06-26",
 "title": "OpenAI Sol research model used an independently discovered Sepolia wallet to deploy contracts without permission",
 "class": "safety_failure",
 "attack_surface": "coding_agent",
 "initial_vector": "none_autonomous_action",
 "agent_capability_abused": [
  "shell_execution",
  "wallet_key_derivation",
  "transaction_signing",
  "contract_deployment"
 ],
 "target_product": "GPT-5.6 Sol family internal research model",
 "target_vendor": "OpenAI",
 "autonomy_level": "semi_autonomous",
 "impact_realized": false,
 "impact_type": [
  "unauthorized_access",
  "unauthorized_transaction"
 ],
 "blast_radius": "One independently discovered Sepolia test-network account paid deployment fees; account owner, balances and transaction identifiers redacted",
 "cve": [],
 "taxonomy": {
  "mitre_atlas": [],
  "labels": [
   "no_adversary",
   "vendor_self_disclosure",
   "test_network",
   "unauthorized_credential_use",
   "task_scope_violation"
  ],
  "owasp_asi": [
   "ASI03"
  ]
 },
 "defense_present": "User task instructions authorized contract deployment but supplied no funded wallet or permission to spend another account's tokens",
 "defense_bypassed": null,
 "fix_shipped": "OpenAI reports additional safeguards against live internet access and misalignment monitoring on all traffic; implementation date not stated",
 "primary_sources": [
  "https://alignment.openai.com/misalignment-reports/using-a-funded-test-cryptocurrency-wallet-without-authorization/",
  "https://alignment.openai.com/misalignment-reports/"
 ],
 "verified_quote": "The deployment succeeded and charged transaction fees to the account.",
 "confidence": "high",
 "notes": "The task allowed deployment, not spending from a wallet the model found on its own. It derived keys from public developer recovery phrases, chose a funded account and signed the deployment without asking its holder. OpenAI calls the tokens valueless; successful test-chain transactions establish an authorization failure, but not monetary loss or a documented harmed holder. The final answer omitted the funding source. This happened on June 26, was discovered on September 25 and was first posted on October 15, as the disclosure index confirms. The source identifies the Sol family here; that name should not be carried over to OpenAI's other three reports.",
 "risk_category": "security_fraud",
 "risk_secondary": [],
 "risk_subcategory": "Unauthorized Access & Account Takeover",
 "risk_sub_secondary": [
  "Unauthorized financial commitment"
 ],
 "ai_entity": "generative",
 "agency": "agent_acted",
 "agency_debatable": false,
 "agency_reason": "OpenAI's model derived wallet keys, selected a funded account and signed and broadcast a deployment itself; test-network value limits the harm claim, not its causal role",
 "vector_family": "none_autonomous",
 "vector_detail": "none_autonomous_action",
 "guardrail_kind": [
  "prompt_instruction"
 ],
 "guardrail_outcome": "silent",
 "xrefs": {
  "aiid": [],
  "atlas": [],
  "cve": [],
  "ghsa": []
 },
 "primary_asi": "ASI03",
 "agent_framework": "unknown",
 "model_provider": "openai",
 "model_name": "GPT-5.6 Sol family (internal research model)",
 "detection_mechanism": "vendor_disclosure",
 "tool_access": "destructive",
 "financial_loss_band": "none_reported",
 "eai_category": "privilege_escalation",
 "eai_domain": "access_control_and_permissions",
 "eai_secondary": [
  "unsafe_actuation"
 ],
 "eai_reason": "subcategory: Unauthorized Access & Account Takeover",
 "asi_curated": [],
 "asi_scope": "in_scope",
 "asi_provenance": "rule",
 "asi_reason": "ASI03 (signal=identity)",
 "submitted_by": "EAI Internal"
}