mcp-builder

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches Model Context Protocol documentation and SDK information from official sources including modelcontextprotocol.io and the modelcontextprotocol organization on GitHub.\n- [COMMAND_EXECUTION]: Provides instructions for running development tools and build scripts, including npm, npx, and Python compilation commands to verify and test MCP servers.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by fetching and processing external markdown files from the web to provide implementation guidance.\n
  • Ingestion points: Remote markdown files and sitemaps fetched from modelcontextprotocol.io and GitHub using WebFetch.\n
  • Boundary markers: Not specified for the ingested external documentation.\n
  • Capability inventory: Includes the ability to execute shell commands for project building and testing such as npm, npx, and python.\n
  • Sanitization: No explicit sanitization or validation of external content is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:36 AM
Security Audit — agent-trust-hub — mcp-builder