Cases · Stage of use: in testing · Severity: moderate · 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 |
| Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address Googlemoderate · earliest source 2026-06-09 | security breach | moderate | 2026-06-09 |
Showing 1–2 of 2. Or take the JSON.