The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses dynamic context injection (!command syntax) in the SKILL.md file to automatically execute git status, git branch, git diff, and git log. These are common read-only operations used to provide context for commit message generation and are performed using standard Git CLI tools.
[PROMPT_INJECTION]: The skill processes repository data, such as diffs and log history, which constitutes an indirect prompt injection surface. 1. Ingestion points: Output from git status, git diff, and git log is read into the agent's context. 2. Boundary markers: None are specified to separate the repository data from the instructions. 3. Capability inventory: The skill can execute Git commands and write to local files as defined in the allowed-tools list. 4. Sanitization: No sanitization of the Git command output is performed. However, given the skill's narrow scope and local-only operations, the risk is minimal.
[SAFE]: The skill does not perform any network operations, access sensitive system files (like SSH keys or credentials), or attempt to persist across sessions. All operations are local to the repository and consistent with its stated purpose.

commit