ClawHub

helpdesk

Security checks across malware telemetry and agentic risk

Overview

This helpdesk skill is purpose-aligned but too underspecified for a ticketing integration that uses an API key and may affect support communications.

Review before installing. Only use this with a least-privilege helpdesk API key after verifying what scripts/helpdesk.py is, which helpdesk service it contacts, and what data it sends. Require explicit confirmation before any ticket changes or customer-facing communications.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill’s activation guidance is vague enough that an agent could invoke it for loosely related 'support' or 'communication' tasks without the user clearly intending to contact an external helpdesk system. In a skill that likely performs ticketing actions and may transmit data using an API key, overly broad use conditions increase the risk of unintended external actions or disclosure of user information.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation mentions an API credential but does not clearly warn that the skill likely sends data to an external ticketing platform. Users or calling agents may therefore provide sensitive support content without understanding that it will leave the local environment, creating a meaningful risk of accidental data exposure.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal