up-to-date
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Executes local shell commands including 'git status', 'git fetch', 'git log', and 'gh' CLI tools to gather repository state and remote activity.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, specifically git commit messages and GitHub PR/issue descriptions, which could contain malicious instructions.
- Ingestion points: Git logs via 'git log' and GitHub metadata via 'gh pr list' and 'gh issue list' as described in the Steps section of SKILL.md.
- Boundary markers: None explicitly defined for command outputs; however, the skill instructs the agent to summarize the activity rather than treat it as authoritative instruction.
- Capability inventory: Includes network operations via 'git fetch' and 'gh' calls, and potential file modifications via 'git pull', 'git rebase', or 'git merge' (though these require explicit user confirmation).
- Sanitization: Not explicitly implemented beyond high-level instructions to report only verified facts and summarize changes rather than repeating every line.
Audit Metadata