Video Maker Browser

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:39 PM UTC
• Version:
  1.0.0

Overview

This is a coherent cloud video-making skill, but users should understand it sends prompts and media to NemoVideo and may create a temporary token/session automatically.

Install only if you are comfortable sending video, image, audio files, prompts, and session data to NemoVideo's cloud service. Use a limited-purpose NEMO_TOKEN when possible, avoid confidential media unless you trust the provider's privacy practices, and expect the skill to create a remote session or starter token if no token is configured.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The catch-all rule routes "Everything else" to the SSE backend, which can cause ordinary user messages to be transmitted to a third-party service without clear user intent or tight scope boundaries. In a browser-based media tool that uploads assets and sends prompts to a cloud API, broad routing increases the chance of accidental data disclosure and unexpected external actions.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill describes local-seeming editing behavior but does not prominently warn that user prompts and uploaded media are sent to a remote cloud rendering service. This can mislead users about where potentially sensitive videos, images, and metadata are processed, undermining informed consent and privacy expectations.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill instructs automatic token acquisition and session establishment before handling requests, while explicitly telling the agent to hide technical details from the user. That creates undisclosed network activity and account/session creation on the user's behalf, which is risky because it occurs without transparent notice or opt-in.

VirusTotal

66/66 vendors flagged this skill as clean.