commit
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses dynamic context injection (the
!syntax) in SKILL.md to gather repository information. - Evidence: Shell commands
git diff --staged,git branch --show-current, andgit log --oneline -5are used to populate the agent's context. - Analysis: These commands are benign, executed locally, and are directly required for the skill's primary functionality.
- [PROMPT_INJECTION]: The skill processes output from Git commands which serves as a surface for indirect prompt injection.
- Ingestion points: Output of
git diff --stagedandgit log --oneline -5in SKILL.md. - Boundary markers: None present.
- Capability inventory: Tool calls for
git commitas defined in SKILL.md. - Sanitization: No explicit sanitization or filtering of Git output is performed.
- Analysis: While the surface for indirect prompt injection exists, the risk is inherent to the primary purpose of a Git automation skill and is considered acceptable.
Audit Metadata