The Agent Skills Directory

[SAFE]: The skill consists exclusively of instructional Markdown documentation. It defines rules for security, performance, and code quality without including any executable scripts, binary files, or automated tasks.
[NO_CODE]: No functional code or automation scripts are present in the skill; it serves solely as a knowledge base and instructional guide for an AI agent.
[PROMPT_INJECTION]: The skill is designed to process user-provided code for review, which creates an ingestion point for untrusted data. However, the skill lacks any exploitable capabilities that could be abused via prompt injection within the reviewed code. 1. Ingestion points: User-provided code snippets or file contents processed by the agent. 2. Boundary markers: The instructions do not specify the use of delimiters or ignore warnings when processing input code. 3. Capability inventory: The skill's functionality is limited to generating text-based review responses. 4. Sanitization: No input validation or sanitization of the analyzed code is performed.

code-reviewer