The Agent Skills Directory

[SAFE]: No security issues were identified. The skill defines a specialized workflow for code quality gating and refactoring within a developer environment.
[PROMPT_INJECTION]: The instructions establish a strict operational framework for reviews. While the language is authoritative (e.g., 'mandate', 'automatic fail'), it is contextually bound to the code review logic and does not target agent safety filters or attempt to bypass platform restrictions.
[DATA_EXFILTRATION]: The skill operates on code inputs and does not attempt to access system credentials, SSH keys, or external network resources. It is limited to the files explicitly provided for review.

code-review