The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of local shell commands via git. Specifically, it uses git status, git diff, git log, git add, and git commit. While these are necessary for the skill's purpose, they represent a standard command execution surface.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository that could potentially influence the agent's behavior.
Ingestion points: Data is ingested through git diff (content of files being committed), git log (previous commit messages), and user-supplied arguments (instructions/file paths).
Boundary markers: The instructions do not define boundary markers or explicit delimiters to prevent the agent from following instructions embedded within the file diffs or previous logs.
Capability inventory: The skill has the capability to modify the local git repository using git add and git commit.
Sanitization: There is no mention of sanitizing or escaping the content retrieved from git diff or git log before the agent uses it to generate the commit subject or body.

commit