Skills
skills/secondsky/claude-skills/ai-sdk-ui/Gen Agent Trust Hub

ai-sdk-ui

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides structured documentation and code templates for integrating the Vercel AI SDK into React and Next.js applications. It does not contain malicious logic or hidden behaviors.- [COMMAND_EXECUTION]: A helper shell script, scripts/check-versions.sh, is included for manual package version auditing. It uses standard shell environment detection and sources a local utility file to perform version checks across common AI SDK packages.- [SAFE]: The skill demonstrates high security awareness by providing explicit warnings in templates (e.g., custom-message-renderer.tsx) against the use of dangerouslySetInnerHTML with untrusted content. It provides safe implementation patterns using isomorphic-dompurify and react-markdown to mitigate Cross-Site Scripting (XSS) risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 02:28 PM