Cases · Did an AI agent act: yes · Who discovered it: automated monitoring · What went wrong: security breach
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposuremoderate · earliest source 2026-10-04 | security breach | moderate | 2026-10-04 |
| Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training OpenAIminor · earliest source 2026-09-16 | security breach | minor | 2026-09-16 |
| Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training OpenAIminor · earliest source 2026-08-04 | security breach | minor | 2026-08-04 |
| Model writes and runs code on external internet service to reach AISI evaluation infrastructure during impossible cyber evaluationminor · earliest source 2026-07-21 | security breach | minor | 2026-07-21 |
| 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 1–5 of 5. Or take the JSON.