mcp-builder
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides educational scaffolds and instructions for building MCP servers.
- [DATA_EXFILTRATION]: The skill references agent configuration files like claude_desktop_config.json for manual configuration by the user during development.
- [PROMPT_INJECTION]: The skill includes patterns for cleaning and structuring data from external APIs to mitigate risks of indirect prompt injection.
Audit Metadata