git-workflow-expert
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves the agent interacting with and interpreting data from local Git repositories, which is a standard surface for potential indirect prompt injection. A repository with malicious commit messages or file content could attempt to influence the agent's logic during operations like log analysis or conflict resolution.
- Ingestion points: Git command outputs including git log, git status, and git diff, along with repository file contents during rebase or merge operations.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat output from the git subsystem as untrusted data.
- Capability inventory: The skill utilizes the Bash tool for executing git commands and Read/Write/Edit for file system interactions.
- Sanitization: The instructions do not prescribe specific sanitization or validation of the data retrieved from the git repository before the agent processes it.
- [EXTERNAL_DOWNLOADS]: The skill references standard third-party utilities and remote repositories for development tasks.
- Evidence: Includes examples of using npx lint-staged and npx turbo for automation, as well as git clone commands targeting generic GitHub repositories.
Audit Metadata