ai-sdk

Pass

Audited by Gen Agent Trust Hub on Oct 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing official AI SDK packages and providers from Vercel's NPM registry, including ai, @ai-sdk/react, @ai-sdk/openai, and others. These originate from a trusted organization.
  • [SAFE]: The documentation actively promotes security best practices, such as using instructions to define agent behavior instead of the system role to mitigate prompt injection risks. It also defaults MCP (Model Context Protocol) redirects to error to prevent Server-Side Request Forgery (SSRF).
  • [SAFE]: No obfuscation, malicious persistence mechanisms, or unauthorized privilege escalation attempts were detected. All technical instructions are consistent with professional development for the Vercel AI SDK environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 3, 2026, 11:13 AM