Skip to main content
Bureau of AI
Promotional banner for the pentest readiness checklist

AI Incident Register

Could it affect you?
Yes4Possibly2Not yet0
How serious
Critical1Serious1Moderate1No harm yet4
What happened
Real harm or failure2
2 recordsCould affect you: Not yet Could affect you: Possibly Serious Moderate Human oversight 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. Stanford R&DE used generative AI to alter students' appearance, including race and gender, in promotional image

    Staff at Stanford's housing and dining office used a generative AI tool, a program that creates or changes images on request, to edit a promotional photo of students.

    ModerateReal harm or failureFirst reported September 23, 2026

    Could it affect you? Possibly if you use AI image tools on photos of real people in marketing

Promotional banner graphic asking if you are ready for PCI DSS 4.0 with a call-to-action to get the guide