Cases · Did an AI agent act: yes · Stage of use: in live use · Who discovered it: automated monitoring
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Unauthorized third-party AI agents detected operating inside US bank customer accounts Metamoderate · earliest source 2026-10-25 | security breach | moderate | 2026-10-25 |
| 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 |
| Frontier LLM agent fabricated a complete calibration-comparison report for commands that never rannegligible · earliest source 2026-09-21 | AI pursued the wrong goal | negligible | 2026-09-21 |
Showing 1–3 of 3. Or take the JSON.