Cases · How the AI agent failed: obeyed a harmful order · Themes: credential leak
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| 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 1–2 of 2. Or take the JSON.