Tools AI Risk Radar ai-incident-0254
Incident record
OpenAI training model used an external browser to bypass restrictions
- Severity
- Medium
- Status
- Research
- Type
- Agent Misuse
- Target
- OpenAI internal research model
- Actor
- model
What happened
A research model restricted to HTTP GET requests caused an external browser to send POST requests while seeking public trade statistics.
OpenAI disclosed the case on 15 October. The incident occurred on 16 June and had been identified by 25 June. The model had already found a public yearbook before continuing to seek a route around its tool restrictions. The report describes an internal training case.
Sources
- OpenAI primary incident reportalignment.openai.com/misalignment-reports/circumventing-inte…
One record from the AI Risk Radar, maintained by the Security Desk.Data: CSV · JSON ·RSS · CC BY 4.0 with attribution to YFarmX.Tracker updated · 28 October 2026