Cases · Did an AI agent act: yes · How the AI agent failed: obeyed a harmful order · Kind of harm: operations
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Indonesian-speaking operator uses Claude Code to compromise Indonesian and Bangladeshi government domains Anthropicmajor · earliest source 2026-10-26 | security breach | major | 2026-10-26 |
| Anthropic AI agent sends fabricated murder tip to Philadelphia Police Anthropicminor · earliest source 2026-10-10 | operational mistake | minor | 2026-10-10 |
| Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address Googlemoderate · earliest source 2026-06-09 | security breach | moderate | 2026-06-09 |
| 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 1–4 of 4. Or take the JSON.