chuuni-refiner
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's workflow includes the execution of a local Python script (
scripts/level-guide.py) to obtain stylistic constraints. The script is provided within the skill's file structure and performs safe, deterministic operations by returning JSON-formatted configuration data based on predefined levels. - [SAFE]: The skill includes robust internal guidelines that instruct the agent to prioritize factual accuracy for professional or medical documents and to refuse requests that involve harassment or the creation of misleading information. These guardrails mitigate the risk of the tool being used to generate deceptive content.
Audit Metadata