policy-engine-builder
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill body includes high-priority instructions that attempt to override the agent's normal response patterns.
- Evidence: The 'MANDATORY' block uses phrases like 'STOP' and 'BASE all responses EXCLUSIVELY' to constrain the agent's knowledge sources and ignore its internal reasoning in favor of a specific skill output.
Audit Metadata