The Agent Skills Directory

[SAFE]: The skill functions as a procedural guide for performance auditing and does not implement any executable scripts, shell commands, or network operations.
[EXTERNAL_DOWNLOADS]: The skill references best-practice catalogues from Vercel (e.g., vercel-react-best-practices). These are official resources from a well-known technology provider and are used for documentation purposes.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data such as React source code, performance profiles, and bundle reports (ingestion points). The instructions do not define specific boundary markers or sanitization requirements for this untrusted data. However, the skill does not include any automated tool capabilities, file system writes, or network access, which prevents the exploitation of the injection surface.

react-performance