local-branches-status
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for the agent to execute a series of local git commands to report on branch status. The implementation uses a shell loop to efficiently gather data and does not perform any network operations, external downloads, or privileged actions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git commit messages to generate branch descriptions, representing a potential attack surface.
- Ingestion points:
SKILL.md(Step 3:git logoutput collected into theuniquevariable). - Boundary markers: Absent; commit messages are processed directly to derive intent.
- Capability inventory: The agent uses shell tools (
git,sed,awk,grep) to extract information. - Sanitization: No explicit sanitization of commit messages is performed, though the risk is inherent to the primary function of summarizing repository state.
Audit Metadata