mcp-builder

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides the agent to fetch documentation from official sources, including the modelcontextprotocol.io domain and the official Model Context Protocol GitHub repositories. These are well-known and authoritative resources for the protocol being documented.
  • [COMMAND_EXECUTION]: The implementation and testing phases recommend standard development commands such as npm run build, npx @modelcontextprotocol/inspector, and python -m py_compile. These are used for building and verifying the code authored by the user in accordance with the guide.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it ingests content from external documentation URLs in SKILL.md. While boundary markers and sanitization are absent, the risk is considered safe because capabilities are limited to standard development tools and the ingestion is restricted to official, trusted protocol documentation sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:41 AM
Security Audit — agent-trust-hub — mcp-builder