Youtube Video Creator Ai

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  1.0.0

Overview

This skill is a cloud video-creation connector whose remote uploads and rendering are disclosed and aligned with its stated purpose, but users should treat it as a third-party media-processing service.

Install only if you are comfortable sending video, images, audio, prompts, URLs, and related metadata to Nemovideo's cloud service. Avoid sensitive or regulated media unless you trust that provider's handling and retention practices, and treat NEMO_TOKEN like an API credential.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The manifest and marketing text narrowly describe support for MP4, MOV, JPG, and PNG up to 500MB, but the body documents many more file types plus URL-based ingestion. This mismatch is security-relevant because it hides the true data-ingestion surface from users and reviewers, increasing the chance that sensitive or unexpected content is sent to the remote backend without informed consent or proper policy review.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The upload API accepts arbitrary URLs, allowing the skill to instruct the backend to fetch remote media rather than only process files the user directly provided. That expands the trust boundary and can enable unintended retrieval of private, internal, or attacker-controlled resources by the cloud service, which is materially riskier than the stated purpose suggests.

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The routing rules are broad enough that generic prompts about generating, editing, exporting, or audio/video changes may invoke this skill unexpectedly. Over-broad triggering is dangerous here because the skill can create sessions, upload data, and send user content to an external cloud service, so accidental invocation can cause privacy-impacting actions the user did not clearly intend.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: Although the document mentions a cloud backend in setup text, it does not provide a prominent upfront warning that uploaded media and prompts are transmitted to an external service for processing. This is a privacy and consent issue because users may share personal videos, images, or audio without understanding they leave the local environment and are handled by a third-party backend.

VirusTotal

66/66 vendors flagged this skill as clean.