clarify-to-decide
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional text designed to refine agent logic during user interviews. No executable scripts, network operations, or sensitive file accesses are present.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface as it ingests user-provided topics and choices to generate interviews and recommendations. It implements logical boundaries by directing the agent to cut irrelevant questions and focus on reversal costs, though it relies on the underlying model's safety guardrails for data sanitization.
Audit Metadata