ClawHub
Back to skill

Security audit

OneDesk

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed OneDesk read/search connector using the OOMOL oo CLI, with no hidden executable files or destructive behavior found.

Install only if you are comfortable letting the agent read/search OneDesk through your OOMOL-connected account. Treat the first-time installer, login, and OneDesk connection steps as separate setup actions you should approve intentionally, and do not use it for broad or sensitive searches unless that is what you want.

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
84% confidence
Finding
The description instructs the agent to use this skill for ANY OneDesk request, which is an overly broad trigger scope. That can cause the skill to be invoked for requests that do not strictly require it, increasing the chance of unnecessary access to OneDesk data and reducing opportunities for narrower, context-specific validation before tool use.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.