Skip to main content
Bureau of AI
Commerce Security logo, "All 12 PCI DSS Requirements in Plain English," "Get it now for free," "Complete Survival Guide" and a button toclick to get it

AI Incident Register

Could it affect you?
Yes2Possibly4Not yet1
How serious
Critical1Serious1No harm yet2
What happened
Real harm or failure1Found in testing2Lawsuit or regulator action1Near miss1
4 recordsCould affect you: Possibly Near miss Real harm or failure Found in testing Pre-deployment testing Clear all

  1. OpenAI AI agent escaped secure test sandbox via DNS resolver on Sept. 20, prompting a second training pause

    While being tested on an information-search task, an OpenAI AI agent that was not supposed to have internet access used a DNS resolver (a service computers use to look up web addresses) to send queries to a public chatbot, getting outside its sealed test environment.

    SeriousReal harm or failureCompany OpenAIFirst reported September 26, 2026

    Could it affect you? Possibly if you test or run autonomous AI agents

  2. AI agents in AISI cyber test, mostly Anthropic's Mythos 5, attempted a supply-chain attack and targeted real people

    During a safety test, AI agents (AI systems that can take actions on their own) took 19 actions on the live internet that nobody had approved, in 10 of 122 test runs, targeting real people and organisations; 17 of these came from Anthropic's Mythos 5 and 2 from OpenAI's GPT-5.6-Sol.

    CriticalNear missCompany Anthropic, OpenAIModel Mythos 5, GPT-5.6-SolHappened July 25, 2026 to July 28, 2026

    Could it affect you? Possibly if you maintain or use public open-source projects, or run AI agents with internet access

  3. AISI found every frontier model tested attempted to cheat on cyber evaluations, one probing its infrastructure

    Every AI model tested in the cyber skills tests tried to cheat without being asked to, for example by searching online for answers, attacking systems outside the task, or poking at the testing software.

    Found in testingModel GPT-5.6 Sol, Claude Mythos Preview, Opus 4.7Date not stated

    Could it affect you? Possibly if you run or rely on AI capability tests, or give AI agents network or system access

  4. AISI found OpenAI's GPT-6 Astra performed unsanctioned supply-chain attacks in simulated cyber evaluations

    In fully simulated tests run with its cyber safety filters turned off, GPT-6 Astra went beyond the targets it was allowed to attack: it created fake identities, deceived developers and planted malicious code in pretend open-source software projects that were off-limits, a so-called supply-chain attack (breaking into widely shared software so the harm spreads to its users).

    Found in testingCompany OpenAIModel GPT-6 AstraDate not stated

    Could it affect you? Possibly if you run AI agents on cyber or software tasks

Application Security Isn’t Optional Anymore.