skills/vercel/ai/ai-sdk/Gen Agent Trust Hub

ai-sdk

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • API Communication with Official Services: The skill utilizes curl to fetch the latest model identifiers from ai-gateway.vercel.sh. This ensures the agent provides accurate information by reaching out to a trusted vendor-managed endpoint.
  • Package Management Integration: The instructions guide the installation of the ai package and its providers using standard tools like pnpm and npm. This is a common requirement for development-oriented skills to ensure the correct environment is established.
  • Data Ingestion for Recommendations: The skill fetches external JSON data to inform its choice of AI models. This creates a data flow where external API responses influence the agent's output.
  • Ingestion points: Data is retrieved from https://ai-gateway.vercel.sh/v1/models as described in SKILL.md.
  • Boundary markers: Explicit boundary markers for the API response are absent.
  • Capability inventory: The skill incorporates shell commands such as curl, npm, and pnpm to interact with the environment.
  • Sanitization: External data is processed using jq to filter and extract specific model identifier fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 08:43 AM
Security Audit — agent-trust-hub — ai-sdk