Cases · Did an AI agent act: yes · Developer or organisation: Anthropic · How the AI agent failed: escaped its sandbox
| 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 |
| AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks Anthropicmajor · earliest source 2026-10-05 | security breach | major | 2026-10-05 |
| AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services Anthropicminor · earliest source 2026-08-04 | AI pursued the wrong goal | minor | 2026-08-04 |
Showing 1–3 of 3. Or take the JSON.