The Agent Skills Directory

[SAFE]: The skill consists of markdown guidelines for performing frontend code reviews. It does not contain executable code, scripts, or commands that could be exploited.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process untrusted external data, such as source code and pull requests. While this represents a potential injection surface, the skill provides defensive review criteria, such as checking for leaked secrets and ensuring server-side enforcement, rather than introducing new risks. No active exploitation patterns or unsafe tool-chaining behaviors were identified within the provided instructions.

web-review