AI SDK v6 UI
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Category 4] (LOW): The skill references the
@ai-sdk/reactpackage. This is a legitimate package maintained by thevercelorganization, which is a verified and trusted source. - [Category 8] (INFO): As this skill defines UI patterns for chat interfaces, the resulting application will naturally process untrusted data (model responses). The patterns include tool approval workflows (
addToolApprovalResponse), which is a security best practice for managing the risks of indirect prompt injection by requiring human-in-the-loop validation for side effects. - [Overall Verdict] (SAFE): The content is purely instructional, follows library best practices, and lacks any patterns related to exfiltration, obfuscation, or unauthorized execution.
Audit Metadata