ai-sdk
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches model configuration and lists from Vercel's official AI Gateway (ai-gateway.vercel.sh). These references are to a well-known service and are documented neutrally.
- [COMMAND_EXECUTION]: Utilizes common CLI tools like
curl,jq, andgrepto retrieve and search technical documentation and model identifiers. These actions are limited to metadata retrieval and local file searching. - [PROMPT_INJECTION]: Instructs the agent to prioritize information found in current documentation over its potentially outdated internal training data. This is a standard accuracy-focused instruction and does not attempt to bypass safety filters.
Audit Metadata