The Agent Skills Directory

[SAFE]: The skill uses standard development tools such as git status, git diff, and git log for their intended purposes of reviewing and committing code.
[SAFE]: It implements safety-conscious instructions, such as explicitly forbidding remote pushes without user consent and requiring the use of git hooks.
[INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface due to the processing of untrusted code diffs and logs, which is necessary for its function.
Ingestion points: Data enters the context via git diff and git log commands as specified in SKILL.md to evaluate the current workspace state.
Boundary markers: Absent; there are no explicit delimiters or warning instructions used to separate the content of code changes from the agent's instructions.
Capability inventory: The skill is limited to git-related subprocess calls for reading repository state and executing commits.
Sanitization: Absent; the skill does not perform escaping or filtering on the data retrieved from the local git repository.

commit