github
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and git to perform repository-related tasks.
- [EXTERNAL_DOWNLOADS]: The skill includes instructions to install the 'gh' CLI via trusted repositories (brew, apt).
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via GitHub data. * Ingestion points: External content is read through commands like 'gh pr view' and 'gh issue list' as noted in SKILL.md. * Boundary markers: There are no markers to distinguish external data from instructions. * Capability inventory: The skill can commit code, push changes, and create PRs as seen in the 'Yeet' workflow in SKILL.md. * Sanitization: No sanitization of GitHub API responses is mentioned.
Audit Metadata