Video Editor Simple

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:40 PM UTC
• Version:
  1.0.0

Overview

This is a coherent cloud video-editing skill, but users should know that media, URLs, and edit prompts are sent to NemoVideo's backend.

Install only if you are comfortable sending videos, URLs, edit prompts, and supporting media assets to mega-api-prod.nemovideo.ai. Avoid confidential footage unless the provider's privacy and retention practices are acceptable, and use your own NEMO_TOKEN if you do not want an anonymous token created automatically.

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
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The skill is presented as a simple video-upload editor, but the documented upload/export behavior expands scope to arbitrary remote URLs and many non-video media types. That mismatch can mislead users and reviewers about what data sources the skill can access, and URL-based ingestion can be abused for unreviewed external fetches or unexpected processing of sensitive/internal resources if backend protections are weak.

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The catch-all routing rule sends 'everything else' to the SSE editing backend, which can cause the skill to trigger on overly broad or unrelated prompts. In practice this increases the chance of unintended network transmission of user content to a third-party service and weakens user consent and boundary control around when the skill activates.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs automatic backend connection and anonymous token creation on first use without a clear upfront warning that it will contact an external service and mint temporary credentials. This undermines informed consent, creates unexpected outbound network activity, and may expose user metadata or initiate third-party account state before the user meaningfully opts in.

VirusTotal

65/65 vendors flagged this skill as clean.