build-mcp-server-sdk-v2

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a collection of guides and recipes for the Model Context Protocol (MCP) v2 SDK. It correctly identifies and warns against anti-patterns from previous versions.
  • [DATA_EXPOSURE]: The skill encourages secure development practices by instructing users to store API keys and secrets in environment variables (e.g., in references/examples/server-recipes.md and references/patterns/deployment.md).
  • [COMMAND_EXECUTION]: Code examples use standard MCP transports (stdio and HTTP). The HTTP adapters (@modelcontextprotocol/express, @modelcontextprotocol/hono) explicitly include DNS rebinding protection as a default security feature.
  • [EXTERNAL_DOWNLOADS]: All suggested dependencies are official MCP ecosystem packages or standard development tools (e.g., TypeScript, Zod, Express).
  • [PROMPT_INJECTION]: No malicious prompt injection patterns or instructions to bypass safety guidelines were detected in the documentation or examples.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 03:48 PM