The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's workflow involves executing several git CLI commands: git status to check the current repository state, git diff --staged to analyze code changes, and git log -5 --oneline to understand recent commit patterns. These are necessary for the skill's primary function.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection (Category 8) because it ingests and processes untrusted data from the local repository.
Ingestion points: The agent reads the output of git diff --staged and git log which contains code and comments from the repository.
Boundary markers: Absent; there are no instructions or delimiters used to ensure the agent ignores instructions that might be contained within the code changes themselves.
Capability inventory: The skill utilizes git commands and expects the agent to generate text based on those results.
Sanitization: Absent; the skill does not include logic to filter or escape the content extracted from the repository before it is processed by the AI.

git-commit