question-refiner
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified during the analysis of the 10 threat categories.- [NO_CODE]: The skill is composed entirely of Markdown documentation and prompt instructions, with no executable logic or scripts.- [PROMPT_INJECTION]: Instructions are focused on clarifying user intent and do not attempt to bypass agent safety or reveal hidden system instructions.- [DATA_EXFILTRATION]: The skill does not access the network, sensitive local files, or environment variables.- [EXTERNAL_DOWNLOADS]: No external software packages or remote code executions are utilized by this skill.- [SAFE]: The skill has a safe interaction surface for processing user input. Ingestion points: User research questions (SKILL.md, instructions.md). Boundary markers: Markdown code blocks. Capability inventory: None. Sanitization: None.
Audit Metadata