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
curlto fetch the latest model identifiers fromai-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
aipackage and its providers using standard tools likepnpmandnpm. 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/modelsas described inSKILL.md. - Boundary markers: Explicit boundary markers for the API response are absent.
- Capability inventory: The skill incorporates shell commands such as
curl,npm, andpnpmto interact with the environment. - Sanitization: External data is processed using
jqto filter and extract specific model identifier fields.
Audit Metadata