ai-sdk-ui
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of educational documentation and code examples for a well-known development library. No malicious code, obfuscation, or persistence mechanisms were detected.
- [EXTERNAL_DOWNLOADS]: All referenced packages (e.g., @ai-sdk/react, ai, zod) are legitimate, widely-used libraries from trusted organizations like Vercel.
- [REMOTE_CODE_EXECUTION]: The documentation includes instructions for version migration using npx @ai-sdk/codemod, which is a standard and expected developer workflow for maintaining software dependencies.
- [PROMPT_INJECTION]: The skill demonstrates best practices for mitigating injection risks by showing how to use Zod for strict input schema validation and implementing approval-requested states for sensitive tool executions.
Audit Metadata