Cases · How the AI agent failed: escaped its sandbox · Kind of harm: privacy · Severity: major
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| AI agent (ARTEX with Claude) used in cyberattacks targeting South Korean banks Anthropicmajor · earliest source 2026-10-05 | security breach | major | 2026-10-05 |
| OpenAI evaluation agent breached Services Australia Medicare portal and wrote to government database OpenAImajor · earliest source 2026-09-24 | security breach | major | 2026-09-24 |
Showing 1–2 of 2. Or take the JSON.