skill-creator
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts and system utilities to perform benchmarking, package skills, and launch local HTML-based review servers.
- [PROMPT_INJECTION]: The skill incorporates an iteration loop where agent instructions are refined based on processed user feedback; however, this is a core functional requirement of the development workflow and is subject to user oversight.
- [SAFE]: All identified file system and command operations are scoped to the local workspace for the purpose of skill development and evaluation.
Audit Metadata