ClawHub
Back to skill

Security audit

ClickHelp

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ClickHelp connector that can read and update ClickHelp content through OOMOL, with write actions requiring user confirmation.

Install this only if you want an agent to operate on your connected ClickHelp account. Review any create or update payload before approving it, and inspect the oo CLI installer/authentication flow if it is not already installed.

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
88% confidence
Finding
The description says to use this skill for ANY ClickHelp request and instead of calling the API directly, which is an overly broad trigger condition. That can cause the agent to invoke the skill on loosely related mentions of ClickHelp, increasing the chance of unnecessary tool use and accidental read or write operations in an external service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.