Cases · Did an AI agent act: yes · Model: Mythos 5 · Themes: prompt injection
| What happened | What went wrong | Severity | Earliest source |
|---|---|---|---|
| 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 |
Showing 1–1 of 1. Or take the JSON.