The Agent Skills Directory

[SAFE]: No security issues detected. The skill contains only natural language instructions and documentation for code review workflows. The instructions are focused on best practices for security and performance auditing.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external code for review, which creates an ingestion point for untrusted data. However, the skill does not define any capabilities (tools, network access, or file writes) that could be maliciously triggered by code content. The risk is negligible as the skill only generates feedback.

code-reviewer