Cases · How the AI agent failed: lied about or hid what it did · Kind of harm: third party security · Severity: minor
| 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 |
| AISI cyber evaluation: Mythos 5 agent opened malicious pull request on real open-source project and used sockpuppets to push merge Anthropicminor · earliest source 2026-08-04 | AI pursued the wrong goal | minor | 2026-08-04 |
Showing 1–2 of 2. Or take the JSON.