The Agent Skills Directory

[SAFE]: The skill follows security best practices and does not exhibit malicious patterns. Its core functionality is focused on git workflow management and commit message quality.
[DATA_EXPOSURE]: The instructions include a mandatory compliance check to ensure no keys, tokens, or debug logs are included in the diff before a commit is finalized.
[EXTERNAL_DOWNLOADS]: The skill fetches a configuration file (commit-types.ts) from the author's GitHub repository (ruan-cat/monorepo). This is a legitimate vendor-controlled resource used to synchronize commit conventions.
[COMMAND_EXECUTION]: The skill utilizes standard development tools like git and commitlint. It specifically recommends using temporary files (git commit -F) to write commit messages, which effectively prevents shell injection vulnerabilities associated with command-line arguments.
[METADATA_POISONING]: The skill includes an extensive blacklist of known fake and malicious GitHub bot accounts to prevent them from being incorrectly attributed in Co-authored-by trailers.

git-commit