ai-sdk

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to search local files using standard tools like grep and glob within the node_modules directory. This is used to provide the user with relevant documentation and source code snippets from the installed AI SDK packages.
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation content from ai-sdk.dev. This is the official domain for the Vercel AI SDK, which is a well-known and trusted service. This behavior is used to ensure the agent has access to the most up-to-date API references.
  • [CREDENTIALS_UNSAFE]: The documentation mentions an AI_GATEWAY_API_KEY but correctly uses a placeholder (your_api_key_here) and recommends storing it in an .env.local file, following industry best practices for secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 02:04 AM
Security Audit — agent-trust-hub — ai-sdk