ClawHub

Review Editor

Security checks across malware telemetry and agentic risk

Overview

This is a coherent cloud video-editing skill, but users should understand that videos and edit prompts are sent to NemoVideo for processing.

Install this only if you are comfortable sending review footage, edit prompts, and session metadata to NemoVideo’s cloud service. Treat NEMO_TOKEN like a password, avoid uploading confidential or rights-sensitive videos unless you trust the provider’s retention and privacy terms, and review or clear ~/.config/nemovideo/ if you want to remove local service state.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
Routing all unmatched requests to the editing/SSE action is overly permissive and can cause unintended transmission of arbitrary user text to the remote backend. In a skill that automatically connects and processes uploaded media server-side, this broad fallback increases the chance of accidental data disclosure or execution of expensive backend actions without clear user intent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The top-level description emphasizes easy editing but does not clearly warn users that uploaded media is sent to a third-party remote backend for processing. Because videos may contain sensitive personal, workplace, or location data, insufficient disclosure undermines informed consent and can lead to unintended exposure of private content.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs automatic backend connection and silent token/session creation, including anonymous-token acquisition, before the user is clearly warned. This is risky because it initiates external network activity and creates persistent session state without explicit informed consent, which is especially sensitive for a media-upload workflow.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal