ClawHub

Roku Control

Security checks across malware telemetry and agentic risk

Overview

This is a local Roku remote-control skill whose main risk is that its unauthenticated LAN commands can immediately affect real Roku devices.

Install only if you are comfortable letting an agent send remote-control commands to Roku devices on your trusted local network. Confirm the target IP/name before power, app launch, volume, navigation, or text-entry actions, and install the Python dependency from a trusted package source.

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 (3)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README explicitly promotes unauthenticated local-network control of Roku devices, including power, app launch, playback, and text input, but does not warn that using the skill can immediately affect active devices, interrupt viewing, or inject on-screen input into the wrong context. In an agent skill context, missing safety/consent guidance increases the risk of unintended or unauthorized control of household devices, especially because the protocol requires no authentication.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The description notes that the protocol has no authentication, but it does not clearly warn users about the safety implications: anyone able to invoke the skill can control nearby Roku devices, launch apps, inject text into searches, and power off supported TVs. Because the commands operate over the local network and target consumer devices with no auth, misuse could cause unwanted device control, privacy issues from text injection, or disruption in a home environment.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The discovery routine actively scans the local network via SSDP and then queries each discovered Roku for device metadata such as name, model, and serial number, but the script provides no user-facing notice or confirmation before doing so. In an agent skill context, this can surprise users and disclose local network device information beyond what they may expect from a simple 'control my Roku' action, especially if discovery is triggered automatically.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal