The Agent Skills Directory

[SAFE]: The skill instructions and associated metadata do not contain any malicious patterns or attempts to bypass safety guardrails.- [COMMAND_EXECUTION]: The skill utilizes legitimate development tools including git, gh (GitHub CLI), and pre-commit. These tools are invoked correctly for their intended purposes within a local repository context.- [DATA_EXFILTRATION]: Network activity is restricted to retrieving issue metadata from GitHub via the official CLI tool. No sensitive credentials or private files are targeted for exfiltration.- [INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from GitHub issues, presenting a low-severity indirect injection surface. Ingestion points: issue titles and labels from gh issue list. Boundary markers: None. Capability inventory: git commit, git add, and bash. Sanitization: None. The risk is negligible as the data is used for commit metadata generation.

git-commit