The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard git commands including git status, git diff, git ls-files, git add, and git commit to manage the repository workflow.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests and processes untrusted data from the local file system.
Ingestion points: The workflow reads the output of git diff HEAD and the full contents of untracked files as specified in SKILL.md.
Boundary markers: Absent. The instructions do not provide delimiters or specific guidelines to the agent to distinguish between its operational instructions and the potentially adversarial content within the files it reads.
Capability inventory: The agent has the capability to modify the repository state using git add and git commit based on its interpretation of the files.
Sanitization: Absent. There is no evidence of filtering or escaping logic applied to the file contents before they are interpolated into the sub-agent's prompt.

micro-commit