skill-creator
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
npx skillscommand-line interface for searching and adding new capabilities to the agent's environment. - [COMMAND_EXECUTION]: Includes Python automation scripts (
init_skill.pyandpackage_skill.py) that perform local file system operations, such as creating directories, writing template files, and setting execution permissions (chmod 755) for generated scripts. - [EXTERNAL_DOWNLOADS]: Provides instructions and commands to download and install skills from external GitHub repositories. These references target well-known organizations and trusted services like
vercel-labs. - [SAFE]: The skill's implementation follows safe coding practices, such as using
yaml.safe_loadfor parsing metadata and restricting operations to the skill's own directory structure. No evidence of prompt injection, data exfiltration, or obfuscation was found.
Audit Metadata