ClawHub
Back to skill

Security audit

ngrok

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-oriented ngrok connector wrapper that is disclosed and proportionate, though users should understand it relies on an OOMOL-connected ngrok account.

Install this only if you are comfortable connecting ngrok through OOMOL and letting the oo CLI query your ngrok account. Confirm any setup, billing, write, or destructive action before it runs, and avoid using it for unrelated ngrok discussion that does not require account data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger text says to use this skill for ANY ngrok request and whenever a task involves ngrok, which is overly broad and can cause the agent to invoke the skill for incidental mentions rather than clear user intent. That increases the chance of unnecessary tool use, schema inspection, or connector calls against an external service without sufficiently precise scoping.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.