The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard git commands including git status, git log, git diff, and git commit to perform its primary function. It includes explicit instructions to avoid state-changing commands like git add or git reset without express user consent.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from the repository's history and file contents.
Ingestion points: Repository data enters the context via git log --oneline -40 and git diff --cached --no-ext-diff.
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the diff or log output.
Capability inventory: Capabilities are limited to local git operations (git status, git log, git diff, git commit).
Sanitization: There is no evidence of sanitization or filtering applied to the content retrieved from the git repository before it is processed by the agent.

git-commit