The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use git status and git diff to analyze the repository state. These are standard, non-destructive read operations necessary for the skill's primary function of drafting commit messages.
[PROMPT_INJECTION]: The skill processes untrusted data from the local repository. Ingestion points: git diff and git status (SKILL.md). Boundary markers: Absent. Capability inventory: git status and git diff (SKILL.md). Sanitization: Absent. While these represent a surface for indirect prompt injection, the skill is considered safe as the agent's capabilities are restricted to git-based analysis and the intent is well-defined.

git-commit