The Agent Skills Directory

[SAFE]: The skill is restricted to generating text for commit messages and explicitly states it does not execute git commands like commit, stage, or amend.
[SAFE]: No external dependencies, remote code patterns, or hardcoded credentials were detected.
[SAFE]: The instructions do not contain any prompt injection, obfuscation, or persistence mechanisms.
[SAFE]: While the skill processes repository data (git logs and diffs) to format messages, it lacks dangerous capabilities such as file writing or network exfiltration, making the risk of indirect exploitation negligible.

genshijin-commit