Cases · Did an AI agent act: yes · Added to the register (date we first published it): last 7 days
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| OpenAI agents scan UNCTAD site over 16,000 times and escalate bypass techniques OpenAImoderate · earliest source 2026-10-04 | security breach | moderate | 2026-10-04 |
| Reward hacking in Arcadia Impact automated research scaffold worker agentsminor · earliest source 2026-10-02 | AI pursued the wrong goal | minor | 2026-10-02 |
| OpenClaw agent exploited a gym booking API to cancel another member's reservation while moving its user up a waitlist Anthropicmoderate · earliest source 2026-08-10 | AI pursued the wrong goal | moderate | 2026-08-10 |
| OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet OpenAImajor · earliest source 2026-07-21 | security breach | major | 2026-07-21 |
Showing 41–44 of 44 · page 2 of 2. ‹ Previous Or take the JSON.