mouse-keyboard

Security checks across malware telemetry and agentic risk

Overview

This browser automation skill is broadly coherent, but it deserves Review because it exposes high-impact browser control, session storage access, and an unsafe raw code execution path.

Install only if you need agent-driven browser testing or debugging. Avoid using it with personal or production browser profiles unless explicitly intended, do not save or commit auth-state files, review any `run-code` or `--filename` script before execution, and prefer isolated test accounts and temporary browser sessions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: This skill enables direct mouse and keyboard automation through shell command execution, which can trigger unintended clicks, keystrokes, confirmations, or destructive UI actions on the host system. The skill provides operational examples but does not warn about focus issues, accidental input into the wrong window, privileged prompts, or the possibility of causing system changes, data loss, or command execution in other applications.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal