typescript-mcp

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official GitHub repositories and documentation from trusted organizations and well-known services, including the Model Context Protocol (Anthropic), Cloudflare, Hono, and various established tool providers. It also includes examples that interact with well-known public APIs like OpenWeatherMap and ExchangeRate-API.
  • [COMMAND_EXECUTION]: Utility scripts are provided for initializing projects (init-mcp-server.sh) and testing connectivity (test-mcp-connection.sh). These scripts use standard system commands (e.g., mkdir, cat, curl, jq) and package management tools (npm, bun) to automate developer workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill templates demonstrate how to build tools that process user-supplied data. While one example in templates/full-server.ts uses string interpolation for a database table name, the accompanying documentation (references/tool-patterns.md) explicitly warns against SQL injection and demonstrates the correct use of parameterized queries as a security best practice.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:40 AM
Security Audit — agent-trust-hub — typescript-mcp