build-mcp-server-sdk-v1

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a purely educational developer guide for the Model Context Protocol (MCP) TypeScript SDK v1.x. It focuses on technical implementation, protocol specifications, and architectural best practices with no malicious instructions detected.
  • [CREDENTIALS_UNSAFE]: The documentation explicitly identifies hardcoding secrets as an anti-pattern. While the skill contains example credential strings in 'references/patterns/anti-patterns.md', these are clearly labeled as 'BAD' examples to teach developers what to avoid, and the skill correctly recommends using environment variables for sensitive data.
  • [COMMAND_EXECUTION]: The provided code recipes for filesystem and database interactions include built-in security mitigations, such as path traversal validation for file access and read-only 'SELECT' checks for SQL queries.
  • [EXTERNAL_DOWNLOADS]: All external dependencies recommended in the setup guides (e.g., @modelcontextprotocol/sdk, zod, express) are well-known, legitimate packages from the official NPM registry, used for their intended development purposes.
  • [SAFE]: The skill includes extensive documentation on Spec Enhancement Proposals (SEPs) regarding authentication and security, including OAuth 2.1 implementation and DNS rebinding protection, promoting the development of secure software.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 03:49 PM