question-refiner
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists solely of Markdown-based instructions and templates. It does not include any scripts (Python, Node.js, etc.) or binary files.
- [PROMPT_INJECTION] (SAFE): The instructions use strong language (e.g., 'CRITICAL') to define interaction logic, such as requiring clarifying questions before generating output. These are functional directives for the agent's persona and do not attempt to bypass safety constraints or extract system instructions.
- [SAFE] (SAFE): No patterns for data exfiltration, credential exposure, or remote code execution were found. The skill operates entirely within the agent's text generation capabilities.
Audit Metadata