fn-knock MCP Server

• Outcome: Review
• Latest audit: May 28, 2026, 11:31 AM
• Version:
  1.0.1

Overview

This appears to be a real fn-knock administration skill, but it gives an AI broad control over gateway, firewall, tunnel, log, and session operations without enough safety scoping.

Install only if you trust the external fn-knock MCP package and intend to let an AI administer your fn-knock gateway. Protect the HMAC secret, review or pin the package source before use, and require explicit user approval before reset, delete, import, firewall, tunnel, DDNS, scanner, session, or gateway-setting changes.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill exposes numerous high-impact administrative and destructive operations, including firewall resets, configuration changes, session termination, record deletion, and backup import, but the documentation provides no explicit safety warnings, confirmation guidance, or constraints on when such actions should be used. In an AI-agent context, that omission increases the chance of unsafe or unintended execution, potentially causing service disruption, lockout, or loss of audit/configuration data.

VirusTotal

VirusTotal findings are pending for this skill version.