ai-sdk

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches model configuration and documentation from official Vercel domains (ai-gateway.vercel.sh and ai-sdk.dev). These are established, well-known services.
  • [COMMAND_EXECUTION]: Includes instructions for using curl to query available models from the Vercel AI Gateway and grep for searching local source code and documentation. These commands are used for their intended purpose of providing up-to-date SDK information.
  • [REMOTE_CODE_EXECUTION]: Mentions the use of npx @ai-sdk/devtools for local debugging purposes. This targets a package within the official Vercel AI SDK ecosystem.
  • [CREDENTIALS_UNSAFE]: References the use of API keys in .env.local files using standard placeholders (your_api_key_here), which aligns with secure development practices for managing secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 10:36 AM
Security Audit — agent-trust-hub — ai-sdk