The Agent Skills Directory

[SAFE]: The skill instructions define static rules for code auditing and do not include any shell commands, network requests, or file system write operations. It functions entirely as a set of logical checks for an AI agent to apply during code reviews.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The metadata and referenced documentation (MDN) are standard for web development tools.
[SAFE]: While the skill reads user-provided files (a surface for indirect prompt injection), it lacks any high-privilege capabilities (like code execution or internet access) that could be exploited by malicious content within those files.

pseudo-elements