The Agent Skills Directory

[SAFE]: The skill provides a comprehensive and secure workflow for Git operations, emphasizing commit signing and standard conventions. It uses established tools like the Git and GitHub CLIs.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute Git commands for staging, committing, and pushing code. It employs safe patterns such as HEREDOCs to prevent shell injection when handling commit messages.
[PROMPT_INJECTION]: The skill ingests untrusted data from GitHub PR bodies and commit history to automate PR title and description updates, which constitutes an indirect prompt injection surface.
Ingestion points: PR metadata via gh pr view and commit history via git log and git diff.
Boundary markers: While it preserves human-authored sections, it lacks explicit delimiters or instructions to ignore embedded commands in the ingested text.
Capability inventory: The skill possesses the ability to write to the repository via git commit and git push, and modify PRs via gh pr edit.
Sanitization: There is no mention of sanitizing or escaping ingested data before it is processed or rewritten.

wk-commit