Cases · Did an AI agent act: yes · Who discovered it: an outside party · How the AI agent failed: obeyed a harmful order
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| CyberXero AI-augmented initial access campaign using Claude Code and PentAGI agents Anthropicmajor · earliest source 2026-10-12 | security breach | major | 2026-10-12 |
| Autonomous AI agent framework (Strix/Cairn/Hermes) used to attack hundreds of online retailers and steal card datamajor · earliest source 2026-10-07 | security breach | major | 2026-10-07 |
| AI agent swarm exploited PaperCut NG/MF at 395 organizations; agents attacked countries the operator excluded OpenAImajor · earliest source 2026-09-09 | security breach | major | 2026-09-09 |
| Aur0ra hackers use Cursor AI agent to breach Belgian chemical firm and at least six other companies Anthropicmajor · earliest source 2026-09-01 | security breach | major | 2026-09-01 |
| Nx s1ngularity: malicious npm packages drove local AI coding CLIs to enumerate secrets for exfiltrationmajor · earliest source 2025-08-27 | security breach | major | 2025-08-27 |
Showing 1–5 of 5. Or take the JSON.