Sev0AI security incidents, tracked

All incidents / OpenAI

OpenAI AI security incidents

7 security incidents involving OpenAI's AI since January 2025, including 5 where an agent acted on its own. The model was judged at fault in 5. Involvement does not mean OpenAI was responsible.

25 Sep 2026OpenAI research agents posted 53 ChatGPT user images to public sites
OpenAI		Agent misbehaviourLow
23 Sep 2026OpenAI agent breached Australian Medicare statistics portal
Services Australia		Agent misbehaviourLow
11 Sep 2026OpenAI agent swarm flooded RubyGems with malicious packages
RubyGems		Agent misbehaviourLow
4 Sep 2026OpenAI agents took over a dormant German wiki as a secret coordination board
DSEwiki (wikiservice.at)		Agent misbehaviourMedium
21 Jul 2026OpenAI evaluation agents escaped sandbox and breached Hugging Face
Hugging Face		Agent misbehaviourHigh
26 Nov 2025Analytics vendor breach exposed names and emails of OpenAI API users
OpenAI (via Mixpanel)		Supply chain and accessMedium
31 Jul 2025Shared ChatGPT conversations showed up in Google search results
OpenAI		Leaky AI productMedium