ClawHub

Game Music

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed cloud video-music editing skill with privacy and scope caveats, but no artifact-backed malicious or hidden behavior.

Install only if you are comfortable using nemovideo.ai as a cloud processor for gameplay footage, prompts, render state, and session metadata. Avoid sensitive or copyrighted videos unless you have rights to upload them, and be aware the skill may create an anonymous service token/session automatically.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The skill markets itself as a narrow gameplay-music helper, but the documented behavior exposes a much broader remote video-editing surface including uploads, stateful editing, timeline/state inspection, and export orchestration. This capability mismatch is security-relevant because users and host systems may grant trust or trigger the skill under narrower expectations, while their media, prompts, and workflow state are actually sent to a third-party backend with richer operations than disclosed.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The invocation language is broad enough to match generic media-editing or video-generation requests, which can cause the skill to activate outside its intended narrow gameplay-music use case. Over-broad triggering increases the chance of unintended file uploads, prompt transmission to the remote service, and user confusion about which skill is handling their content.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill encourages users to upload gameplay footage and issue editing prompts, but it does not clearly warn that media and instructions are transmitted to a cloud backend for processing. This is dangerous because users may unknowingly disclose private, copyrighted, or sensitive content to a third party under the assumption the skill operates locally or with limited external sharing.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill specifies automatic backend connection and anonymous token acquisition on first open without a clear consent notice. Automatically contacting a third-party service and provisioning credentials before informed user approval creates a meaningful privacy and trust risk, especially because it can disclose client metadata and establish a remote session even before the user chooses to upload content.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal