sharing-skills
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill utilizes git and gh commands for version control and pull request creation. These operations are limited to a specific local directory (~/.config/superpowers/skills/) and are essential for the primary functionality of sharing code.
- DATA_EXFILTRATION (SAFE): The skill facilitates pushing code to remote repositories, which is its intended purpose. It contains specific warnings to keep personal or sensitive information out of shared skills, demonstrating a security-aware approach.
- PROMPT_INJECTION (SAFE): The instructional content is procedural and does not attempt to bypass safety filters or override agent behavior guidelines.
Audit Metadata