ClawHub

Android Control

Security checks across malware telemetry and agentic risk

Overview

This Android-control skill is coherent, but it needs review because it can automatically retry actions as root and capture sensitive screen data without clear consent boundaries.

Install only if you intentionally want an agent to control an Android device. Prefer a test device, keep sensitive screens closed, and require explicit confirmation before screenshots, text entry, settings changes, purchases, messages, or any root-backed action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises direct Android device control and automatic root fallback without a prominent warning that commands may escalate privileges and perform sensitive actions on the user's device. In an agent setting, that omission can cause users or downstream systems to invoke the skill without understanding it may execute privileged device-control operations.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documented screenshot and UI-dump features can expose highly sensitive on-screen content, app structure, notifications, credentials, and personal data, yet no privacy warning or handling guidance is provided. In a remote agent context, these capabilities materially increase surveillance and data-exfiltration risk if used without informed consent and minimization controls.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal