Skip to main content
Bureau of AI
Promotional banner ad for the Penetration Testing Report Kit

AI Incident Register

Could it affect you?
Possibly2
How serious
Critical1Serious1Moderate2No harm yet0
What happened
Real harm or failure1Found in testing3Lawsuit or regulator action1Near miss1
2 recordsNo harm yet Critical Serious Near miss Real harm or failure 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

a promotional banner asking how ready are you for PCI DSS 4.0? With a call-to-action to get the checklist now.