The Agent Skills Directory

[PROMPT_INJECTION]: Potential for indirect prompt injection via untrusted code comments.
Ingestion points: Reads source code files during the review process in Step 3.
Boundary markers: No delimiters or safety instructions are provided to sub-agents to ignore instructions embedded in data.
Capability inventory: Executes git commands, spawns sub-agents via the Task tool, and uses an Edit tool for filesystem modification.
Sanitization: No sanitization or filtering of code comments is performed before processing.
[COMMAND_EXECUTION]: Executes git diff commands to calculate the list of files to be reviewed.

review-comments