babysit
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external GitHub PRs and CI runs which could contain malicious instructions. * Ingestion points: gh pr view, gh pr checks, and gh run view commands in SKILL.md. * Boundary markers: The instructions do not specify any boundary markers to delimit or ignore instructions within the fetched data. * Capability inventory: The skill utilizes gh CLI commands to interact with the environment. * Sanitization: No specific sanitization or validation of the fetched PR data is mentioned.
- [COMMAND_EXECUTION]: The skill relies on executing gh CLI commands to perform its tasks.
- [EXTERNAL_DOWNLOADS]: The skill provides links to official GitHub documentation and the GitHub CLI source code for reference. These references target well-known, trusted sources.
Audit Metadata