ai-sdk-core
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as an educational resource for building applications with the Vercel AI SDK. It includes explicit patterns for security, such as implementing guardrails and PII redaction using language model middleware. \n- [COMMAND_EXECUTION]: The documentation explains how to utilize the Model Context Protocol (MCP) via the
Experimental_StdioMCPTransport, which facilitates communication with local servers through subprocess execution. This is a standard architectural pattern for AI agents. \n- [EXTERNAL_DOWNLOADS]: The provided code snippets demonstrate the installation of reputable and well-known open-source packages from the official npm registry.
Audit Metadata