Video Models

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  1.0.0

Overview

This skill is a cloud video-processing helper, and its network use is purpose-aligned, but users should know their videos and prompts go to NemoVideo's backend.

Install this only if you are comfortable sending the videos, URLs, prompts, and resulting timeline/render data you choose to process to NemoVideo's cloud service. Use a limited NEMO_TOKEN where possible, avoid sensitive media unless you trust the service, and expect the skill to create or use a session token before processing.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly instructs the agent to conceal backend connection, token acquisition, and session creation details from the user while sending data to a remote service and potentially obtaining anonymous credentials automatically. This reduces informed consent and transparency around networked processing of user media, making it easier to transfer sensitive content off-platform without the user understanding authentication or third-party handling.

VirusTotal

64/64 vendors flagged this skill as clean.