Cases · How the AI agent failed: obeyed a harmful order · Model: Claude Code · Quarter of the earliest source we hold: 2026-Q4
| 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 |
Showing 1–1 of 1. Or take the JSON.