github
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices for CLI integrations. No obfuscation, data exfiltration, or malicious instructions were identified.
- [COMMAND_EXECUTION]: Shell execution is limited to the official GitHub CLI binary ('gh') for standard development tasks such as listing pull requests and viewing CI run logs.
- [EXTERNAL_DOWNLOADS]: The skill metadata correctly points to trusted package managers (brew and apt) for the installation of the GitHub CLI, which is a well-known service.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by reading external pull request and issue content, but this is a necessary feature for its intended purpose. 1. Ingestion points: 'SKILL.md' (utilizing 'gh pr view' and 'gh issue list' to read external text). 2. Boundary markers: None defined in the skill body. 3. Capability inventory: Read and write access to GitHub repositories via the authenticated 'gh' CLI. 4. Sanitization: No explicit sanitization or filtering of GitHub content is mentioned.
Audit Metadata