mcp-builder

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill provides purely instructional content and design guidelines for developers creating Model Context Protocol (MCP) servers. It does not contain any executable code or instructions that bypass safety protocols.
  • [EXTERNAL_DOWNLOADS]: The skill includes links to fetch documentation from modelcontextprotocol.io and official GitHub repositories under the modelcontextprotocol organization. These are well-known services associated with the framework the skill is designed to support.
  • [PROMPT_INJECTION]: No evidence of prompt injection, role-play bypasses, or instructions to ignore safety filters was found.
  • [DATA_EXFILTRATION]: The skill does not access sensitive local files or perform unauthorized network operations. Its network activity is limited to fetching public documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 12:09 PM
Security Audit — agent-trust-hub — mcp-builder