ClawHub
Back to skill

Security audit

HiDPI Mouse

Security checks across malware telemetry and agentic risk

Overview

This skill controls the Linux mouse for HiDPI desktop automation, and that broad desktop access is disclosed and aligned with its purpose.

Install only if you are comfortable allowing an agent to move, click, and drag on your live Linux/X11 desktop. Supervise use on sensitive screens, verify coordinates before important actions, and avoid running these scripts with elevated privileges.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The skill is presented as a coordinate-scaling helper for clicks, but the documentation also exposes broader UI automation capabilities including movement, dragging, window targeting, and focus switching. That mismatch matters because it expands the effective privilege and operational scope of the skill beyond what a reviewer or user might reasonably expect, increasing the chance of unintended or unauthorized interaction with applications and data.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documentation instructs use of click, drag, and reset operations that can directly manipulate the desktop state, but it does not clearly warn that these actions may activate windows, modify application state, trigger destructive UI actions, or reset configuration. In a desktop automation context, the absence of explicit safety warnings and guardrails makes accidental misuse more likely, especially when coordinates are inferred from screenshots and may be inaccurate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.