chatml-injection
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses ChatML role tokens to attempt a structural override of agent instructions.
- [PROMPT_INJECTION]: Contains explicit commands to ignore all previous instructions and reveal the system prompt, which are characteristic of prompt injection attacks.
Audit Metadata