ai-sdk
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches model availability data from the official Vercel AI Gateway endpoint (
https://ai-gateway.vercel.sh/v1/models). This is a legitimate operation to ensure the agent uses valid and up-to-date model IDs. - [COMMAND_EXECUTION]: Instructs the agent to use standard CLI tools like
curl,jq, andgrepfor local and remote documentation search and model management. It also provides instructions for using package managers (pnpm,npx) to install official SDK components. - [PROMPT_INJECTION]: Contains instructions for the agent to prioritize the provided documentation and source code over its internal training data. This is a common and safe practice used to ensure accuracy when working with rapidly evolving software libraries and does not represent an attempt to bypass safety filters.
Audit Metadata