git-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely instructional, providing best practices for version control using Git. It does not contain executable scripts or malicious logic.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions guide an agent to review user-provided data such as commit messages, branch names, and pull request descriptions.
- Ingestion points: User input is analyzed against the provided rules in
SKILL.mdandAGENTS.md. - Boundary markers: The instructions do not define specific delimiters for user-supplied strings, relying on the agent's internal reasoning.
- Capability inventory: The skill recommends the use of standard development tools like
gitandgh(GitHub CLI) for executing workflow commands. - Sanitization: No explicit sanitization or escaping of user strings is described, though the commands suggested (e.g.,
git commit -m) are standard practice. - [EXTERNAL_DOWNLOADS]: The skill recommends several industry-standard tools and documentation sources, including official Git documentation, Conventional Commits, and well-known repositories such as the Linux kernel and React. These sources are reputable and documented neutrally.
Audit Metadata