The Agent Skills Directory

[SAFE]: No security issues or malicious patterns were identified in the skill. The instructions and code examples focus exclusively on legitimate frontend performance diagnostic and optimization tasks.
[EXTERNAL_DOWNLOADS]: The skill correctly recommends well-known and trusted tools from established organizations, such as Google's Lighthouse and Chrome UX Report. Dependencies such as web-vitals and TanStack Query are standard in the industry and present no security concerns.
[COMMAND_EXECUTION]: The skill suggests the use of diagnostic CLI tools like npx lighthouse and npx size-limit. These are appropriate for the skill's purpose and are used in a controlled, professional context.
[PROMPT_INJECTION]: The skill involves processing user-provided URLs and application code for analysis, which is an inherent part of its diagnostic function. No evidence of malicious override instructions or safety bypass patterns was found.
[DATA_EXFILTRATION]: No patterns suggestive of unauthorized data access or exfiltration were detected. The performance monitoring strategies described are standard RUM (Real User Monitoring) practices focusing on non-sensitive telemetry.

frontend-performance