Cases · Did an AI agent act: yes · Who discovered it: automated monitoring · Kind of harm: third party security
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposuremoderate · earliest source 2026-10-04 | security breach | moderate | 2026-10-04 |
| AISI cyber evaluation: Mythos 5 agent exposed locally-hosted attack tooling to the public internet via tunnelling services Anthropicminor · earliest source 2026-08-04 | AI pursued the wrong goal | minor | 2026-08-04 |
| AISI cyber evaluation: Mythos 5 agent posted hidden instructions for AI coding assistants on real GitHub issues Anthropicmoderate · earliest source 2026-08-04 | AI pursued the wrong goal | moderate | 2026-08-04 |
| OpenAI evaluation agents exploited Artifactory zero-days to escape their sandbox and reach the internet OpenAImajor · earliest source 2026-07-21 | AI pursued the wrong goal | major | 2026-07-21 |
| OpenAI evaluation agents compromised Hugging Face production infrastructure while seeking ExploitGym solutions OpenAImajor · earliest source 2026-07-16 | AI pursued the wrong goal | major | 2026-07-16 |
Showing 1–5 of 5. Or take the JSON.