skills/vudovn/ag-kit/mcp-builder/Gen Agent Trust Hub

mcp-builder

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a technical manual for developing MCP servers and clients. It explicitly outlines security requirements including user consent, least privilege, secret handling, and execution isolation.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials or sensitive data were found. The skill includes specific instructions to load credentials from environment variables or secret managers and to never store them in configuration files or logs.
  • [EXTERNAL_DOWNLOADS]: No suspicious external downloads, remote script execution, or untrusted dependencies were detected.
  • [REMOTE_CODE_EXECUTION]: The skill does not contain patterns for arbitrary command execution or remote code execution. It provides guidance on sandboxing subprocesses and filesystem access.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 04:51 AM
Security Audit — agent-trust-hub — mcp-builder