The Agent Skills Directory

[SAFE]: The skill serves as a robust educational and procedural resource for code reviews, covering architecture, performance, and security across multiple tech stacks.
[COMMAND_EXECUTION]: The skill is configured to use the Bash tool to run developer-centric commands (lint/test/build), which is a standard and expected capability for a code review assistant.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code files, which is its primary function. While this creates a theoretical surface for indirect prompt injection, it is considered a low-risk, expected behavior for this use case.
Ingestion points: Code files are provided as input in the SKILL.md manifest.
Boundary markers: The skill does not define specific prompt delimiters to separate instructions from the code being reviewed.
Capability inventory: The skill is allowed to use Bash, Read, Grep, Glob, and WebFetch tools.
Sanitization: No explicit sanitization or filtering of input code is described.

code-review-skill