The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and markdown formatting. No executable scripts, binary files, or external network operations were detected.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data in the form of code diffs and file paths, which represents a potential attack surface for indirect prompt injection.
Ingestion points: The agent processes a diff or path/glob provided by the caller as its primary input (SKILL.md).
Boundary markers: No specific delimiters or boundary markers are defined to isolate the processed code from the agent's instructions.
Capability inventory: The skill is restricted to a

review-code