ai-sdk-7
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical reference for Vercel AI SDK v7, providing standard implementation patterns and migration advice.
- [EXTERNAL_DOWNLOADS]: The skill references official Vercel documentation (ai-sdk.dev) and GitHub repositories (github.com/vercel/ai). As Vercel is a well-known service and trusted organization, these references are considered safe and consistent with the skill's purpose.
- [CREDENTIALS_UNSAFE]: The skill provides guidance on managing sensitive data, specifically recommending the use of environment variables for tool approval secrets rather than hardcoding them, which aligns with industry security best practices.
- [INDIRECT_PROMPT_INJECTION]: The skill includes documentation on using Zod for schema validation (inputSchema, contextSchema) and warns about the security implications of allowSystemInMessages, encouraging developers to only use it for trusted history sources.
Audit Metadata