Ai Youtube Video

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

Overview

This is a real cloud video-editing skill, but it can automatically create a NemoVideo session and send broad user prompts or uploaded media to an external backend without tight scoping or an explicit consent step.

Install only if you intend to use NemoVideo cloud processing. Treat uploaded videos, audio, images, URLs, and edit prompts as data sent to a third-party service; avoid sensitive unpublished footage unless you trust that provider, and keep NEMO_TOKEN private.

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: 88% confidence
• Finding: The invocation examples are broad and generic enough that normal conversation like 'export 1080p MP4' or 'edit my raw video footage' could unintentionally trigger the skill. Because this skill performs networked actions, creates backend sessions, and may obtain authentication tokens automatically, accidental invocation can cause unintended uploads or external API use.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The catch-all rule routes 'Everything else' to the SSE editing backend, which lacks meaningful scope limits and can send arbitrary user text to an external service. In context, this is more dangerous because the skill supports automatic backend setup and persistent sessions, so unrelated user requests may be forwarded off-platform without clear consent.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill description explains processing behavior but does not clearly warn users that their uploaded media and editing prompts are sent to a third-party cloud backend. This is a real privacy and consent issue, especially for raw video footage that may contain sensitive personal, biometric, or proprietary content.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill is designed to automatically obtain an anonymous token and store session information, but this behavior is not clearly disclosed to the user. Automatic credential acquisition and storage increase the risk of silent account/session creation and unexpected persistence of access to the external service.

VirusTotal

66/66 vendors flagged this skill as clean.