The Agent Skills Directory

[PROMPT_INJECTION]: The skill requires the agent to ingest and process untrusted data from the repository (via diffs) and user context to formulate commit messages, creating an attack surface for indirect prompt injection.
Ingestion points: Staged repository changes accessed via git diff --cached and user-provided context are interpolated into the agent's workflow.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when analyzing diff content to prevent the agent from following instructions embedded within the code being committed.
Capability inventory: The skill employs shell command execution for core git operations, including git status, git diff, git add, and git commit.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from the file system before it is processed by the agent.

git-commits