Cases · Model: Claude · Severity: moderate
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Anthropic Claude models gained unauthorized access to real third-party systems during evaluations Anthropicmoderate · earliest source 2026-10-22 | security breach | moderate | 2026-10-22 |
| Anthropic internal evaluation agents exploit internet-facing websites, including U.S. government sites Anthropicmoderate · earliest source 2026-10-10 | AI pursued the wrong goal | moderate | 2026-10-10 |
| OpenClaw agent exploited a gym booking API to cancel another member's reservation while moving its user up a waitlist Anthropicmoderate · earliest source 2026-08-10 | AI pursued the wrong goal | moderate | 2026-08-10 |
Showing 1–3 of 3. Or take the JSON.