ClawHub
Back to skill

Security audit

Desktop Automation Hub Free

Security checks across malware telemetry and agentic risk

Overview

This skill clearly describes desktop automation features, but users should treat screenshots, clipboard access, and automated clicking/typing as sensitive capabilities.

Install only if you want an agent to control your desktop. Keep failsafe enabled, verify the active window before clicks or typing, avoid clipboard use for secrets, and require your own confirmation before submissions or other irreversible actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill exposes high-risk desktop control primitives including screenshots, clipboard access, and keyboard/mouse automation without prominent privacy and integrity warnings. In an agent setting, these capabilities can capture sensitive on-screen data or trigger unintended actions in the wrong context if invoked carelessly or by prompt injection.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The form automation example performs blind clicking, typing, tabbing, and submission based only on coordinates and assumed focus, with no validation step. In desktop automation, that can easily cause accidental modification or submission of data into the wrong application or field, especially when used by an autonomous agent.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The cross-window copy/paste workflow normalizes clipboard extraction and transfer without warning that clipboard contents may contain secrets or overwrite existing sensitive data. In an agent-controlled environment, this increases the chance of unintended disclosure, propagation, or corruption of confidential information across applications.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.