Skills
skills/sickn33/antigravity-awesome-skills/vercel-ai-sdk-expert/Gen Agent Trust Hub

vercel-ai-sdk-expert

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill consists of educational material and code templates. All external package references (ai, @ai-sdk/react, @ai-sdk/openai) belong to well-known and trusted organizations (Vercel).\n- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates patterns for handling external data. 1. Ingestion points: The messages array in app/api/chat/route.ts and the input field in the React chat component. 2. Boundary markers: Examples include explicit system prompts to define AI behavior. 3. Capability inventory: Tool calling is demonstrated via the getWeather function, which allows structured execution. 4. Sanitization: The examples leverage zod schemas for tool parameters and structured data generation, providing robust input validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 05:35 PM