Video Maker Editor

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.0

Overview

This is a coherent cloud video-editing skill, but it needs Review because it can automatically use a token, create a remote session, and route broad prompts/media to NemoVideo without a clear consent gate.

Install only if you are comfortable sending video/audio files, edit prompts, metadata, and render state to NemoVideo's cloud API. Use non-sensitive media first, avoid ambient credentials unless intended, and require the agent to ask before setup, upload, SSE editing, or export actions.

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 (4)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The example invocation language is broad enough that ordinary conversation about editing or exporting video could unintentionally trigger the skill. Because this skill performs automatic remote setup and may use existing environment credentials, accidental activation can cause unintended outbound network calls and session creation without clear user intent.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The catch-all rule routes 'Everything else' to the editing SSE action, creating an extremely broad activation surface. In context, that means many unrelated or ambiguous user messages could trigger backend requests, which is more dangerous because the skill automatically connects to a cloud API and can process user media or consume credits.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill discusses uploading clips and cloud rendering but does not provide a prominent user-facing warning that media is transmitted to a third-party cloud API for processing. This creates a privacy and consent risk because users may share sensitive or proprietary media without realizing it leaves the local environment.

Missing User Warnings

Low

• Confidence: 91% confidence
• Finding: The automatic setup instructs the agent to contact remote authentication/session endpoints immediately and to use an existing NEMO_TOKEN if present, but it does not clearly warn the user first. This is dangerous because it can silently use ambient credentials or create anonymous tokens and sessions, exposing metadata and making outbound requests without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.