Back to skill

Security audit

Windows GUI 自动化集成 (中文)

Security checks across malware telemetry and agentic risk

Overview

This is a transparent, instruction-only Windows desktop automation skill, with powerful screen and input capabilities that match its stated purpose.

Install this only if you intentionally want a Windows desktop automation helper. Review the dependent automation skills separately, avoid using it while passwords or private documents are visible, and require confirmation before screenshots, clicks, typing, submissions, or saved logs.

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
90% confidence
Finding
The trigger phrases are broad and overlap with common user requests such as '桌面自动化' and '点击这个窗口', which can cause the skill to activate unexpectedly. Because this skill enables desktop control, screenshots, and application interaction, accidental invocation could lead to unintended system actions or capture of sensitive on-screen information.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill description promotes screenshots, AI visual analysis, and desktop control without clearly warning that these capabilities may expose sensitive on-screen data or perform impactful system actions. In a Windows GUI automation context, lack of consent and safety messaging increases the chance of users triggering operations that leak credentials, personal data, or modify system/application state unintentionally.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.