The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from git diffs, which constitutes an indirect prompt injection surface.
Ingestion points: The agent reviews output from git status and git diff (SKILL.md).
Boundary markers: The instructions lack specific delimiters or directions to ignore instructions embedded within the codebase being reviewed.
Capability inventory: The skill enables the agent to execute git add and git commit commands (SKILL.md).
Sanitization: No data sanitization or filtering is specified for the git command outputs.
[SAFE]: The skill utilizes standard version control tools for their intended purpose and does not perform network operations or execute external code.

commit-atomic