skills/ngrok/skills/run-mcp-gateway/Gen Agent Trust Hub

run-mcp-gateway

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to execute ngrok CLI commands to create secure tunnels, vaults, and secrets. It also uses openssl for secure token generation. These commands are standard operations for the tool provided by the vendor.
  • [SAFE]: The skill implements several security best practices:
  • Credential Management: It uses ngrok's Vaults and Secrets system to manage bearer tokens rather than hardcoding them or passing them as environment variables.
  • Network Isolation: The local MCP server binds to 127.0.0.1 (loopback), ensuring it is only accessible through the ngrok agent.
  • Traffic Policy: The provided traffic policy uses a deny-by-default (401 Unauthorized) catch-all rule and performs server-side authentication using the Bearer tokens stored in secrets.
  • Input Validation: The policy restricts access to a specific path (/mcp).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 06:41 AM