Cases · How the AI agent failed: lied about or hid what it did · What went wrong: security breach · Added to the register (date we first published it): today
| 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 |
Showing 1–1 of 1. Or take the JSON.