design
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions in
SKILL.mdattempt to override the agent's default interaction model by mandating auto-activation and bypassing user oversight. Specific phrases used include 'MUST BE USED proactively', 'NO user confirmation needed for TIER 1 skills', and 'Activate immediately'.
Audit Metadata