mcp-server-builder

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install standard development dependencies including @modelcontextprotocol/sdk, zod, typescript, and @octokit/rest. These are well-known libraries used for the stated purpose of building MCP servers and interacting with the GitHub API.
  • [DATA_EXPOSURE]: The skill demonstrates how to handle credentials using environment variables (e.g., process.env.GITHUB_TOKEN) and includes placeholders for user-provided API keys in configuration examples. This aligns with secure development practices.
  • [COMMAND_EXECUTION]: The skill includes shell commands for project initialization (npm init), dependency installation (npm install), and testing (npx @modelcontextprotocol/inspector). These are standard development workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates building prompts that interpolate user-provided data (e.g., code review or error messages). It follows the best practice of recommending input validation (via Zod) to mitigate potential injection risks at the application layer.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:30 AM
Security Audit — agent-trust-hub — mcp-server-builder