build-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected. The skill serves as a legitimate technical tutorial for software development.
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation and README files from the official Model Context Protocol website and its associated GitHub repositories. These are well-known, trusted sources for the Model Context Protocol ecosystem.
  • [COMMAND_EXECUTION]: Includes standard developer guidance for testing locally developed servers, such as using the timeout command or terminal multiplexers (tmux) to manage process lifecycles.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs developers on how to build tools that process data; it explicitly recommends defensive practices such as Pydantic/Zod schema validation and structured error handling to mitigate risks in the resulting implementations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:10 AM
Security Audit — agent-trust-hub — build-mcp