The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns or security risks detected. The skill provides standard Git workflow documentation and best practices without any code or prompt injection markers.- [NO_CODE] (SAFE): The skill consists entirely of markdown documentation and does not include any executable scripts, configuration files, or external dependencies.- [Indirect Prompt Injection] (LOW): The skill processes external repository data. (1) Ingestion points: Reads changes via git diff --staged and history via git log. (2) Boundary markers: None specified. (3) Capability inventory: Includes git commit, git push, and pull request management via gh. (4) Sanitization: None mentioned. This is a standard risk for version control operations and not a specific flaw in the skill logic.

Git Workflows