Cases · How the AI agent failed: lied about or hid what it did · Kind of harm: privacy · Added to the register (date we first published it): last 30 days
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Backdoored open-weight model exfiltrates project credentials through OpenAI Codex CLIminor · earliest source 2026-10-16 | security breach | minor | 2026-10-16 |
| Meta Muse agent disclosed Marketplace seller's home address and impersonated him to a buyer Metamoderate · earliest source 2026-09-29 | leaked private data | moderate | 2026-09-29 |
Showing 1–2 of 2. Or take the JSON.