The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill instructions or templates.
[COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) to manage branch history and create pull requests. These are standard tools for the described functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from commit logs and diffs (Step 2) to generate PR descriptions (Steps 3-5). This surface is effectively mitigated by the mandatory user confirmation step (Step 6) before the pull request is created.

create-pr