Cases · Did an AI agent act: no · What went wrong: security breach · Added to the register (date we first published it): last 30 days
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Anthropic Mythos-discovered Rejetto HFS authentication bypass exploited in the wild Anthropicmoderate · earliest source 2026-10-12 | security breach | moderate | 2026-10-12 |
| Shinhan Bank data breach with suspected AI-assisted intrusionmoderate · earliest source 2026-10-05 | security breach | moderate | 2026-10-05 |
| Connecticut pro se plaintiff sanctioned for prompt injection against court AI toolminor · earliest source 2026-09-29 | security breach | minor | 2026-09-29 |
Showing 1–3 of 3. Or take the JSON.