Cases · Did an AI agent act: yes · Model: GPT-5.6 Sol · What set it off: a task it could not do
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| 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 1–1 of 1. Or take the JSON.