ai-sdk

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Retrieves live model metadata from the official Vercel AI Gateway API.
  • Evidence: Uses curl -s https://ai-gateway.vercel.sh/v1/models in SKILL.md and references/ai-gateway.md to fetch current model IDs from a well-known service.
  • [SAFE]: Guides the installation of official AI SDK packages.
  • Evidence: Recommends installing the ai package and provider libraries (e.g., @ai-sdk/openai) via standard package managers in SKILL.md.
  • [SAFE]: Implements local documentation searching.
  • Evidence: Uses grep to scan node_modules/ai/docs/ and node_modules/ai/src/ in SKILL.md for up-to-date API information.
  • [SAFE]: Adheres to secure configuration practices for API keys.
  • Evidence: Instructs users to store AI_GATEWAY_API_KEY in .env.local in references/ai-gateway.md, following industry best practices for secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 03:33 PM
Security Audit — agent-trust-hub — ai-sdk