mcp-builder
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides official development patterns and utility scripts for the Model Context Protocol. It adheres to security best practices by advising the use of environment variables for sensitive credentials and implementing strict input validation using Zod and Pydantic. All external references point to official documentation or trusted technology repositories.
- [COMMAND_EXECUTION]: The evaluation script (
scripts/evaluation.py) is designed to launch and interact with local MCP server processes using user-specified commands and arguments. This behavior is the intended functionality for local development and testing of MCP integrations. - [EXTERNAL_DOWNLOADS]: Dependencies and documentation references target well-known organizations and official services, such as the Anthropic and Model Context Protocol repositories on GitHub and standard package registries (npm/PyPI).
- [PROMPT_INJECTION]: The evaluation harness processes test questions from external XML files. To maintain agent behavior during these tests, the script employs a structured system prompt with explicit boundary markers for summary, feedback, and response output sections.
Audit Metadata