The Agent Skills Directory

[SAFE]: No security issues detected. The skill provides instructional content and suggests standard development commands for code auditing and quality assurance.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to process untrusted source code and git diffs (SKILL.md). Ingestion points: code content and diff outputs. Boundary markers: none provided. Capability inventory: suggests running development tools like git, cargo, and npm. Sanitization: none. This is an expected risk surface given the skill's primary purpose.
[COMMAND_EXECUTION]: The skill provides instructions to run common development utilities such as git, cargo, and npm (SKILL.md) for testing, formatting, and linting, which is appropriate for a code review workflow.

code-review