Filtrix Video Gen

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:18 PM UTC
• Version:
  0.1.0

Overview

This skill does what it advertises: it sends user-provided prompts or images to Filtrix to generate and download videos, with the main risk being trust in that external service.

Install only if you trust Filtrix and the publisher with your prompts, selected input images, generated-video metadata, API key use, and account credits. Avoid sending sensitive or regulated media unless approved for that service, prefer a scoped or revocable API key if available, and set FILTRIX_MCP_API_KEY explicitly rather than relying on a generic MCP_API_KEY environment variable.

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 (2)

Missing User Warnings

Low

• Confidence: 95% confidence
• Finding: The skill instructs users to send prompts, images, and request metadata to a third-party Filtrix MCP endpoint but does not provide a clear privacy or data-transmission warning. Users may unknowingly submit sensitive text or media to an external service, which is especially risky for enterprise, regulated, or personal content workflows.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The documentation explicitly directs use of a remote MCP endpoint for video generation and status polling, which necessarily sends user prompts and often image inputs off-platform to a third-party service. Because there is no accompanying notice about external transmission, retention, or privacy implications, users and integrators may unknowingly disclose sensitive images or confidential prompt content to the remote provider.

VirusTotal

66/66 vendors flagged this skill as clean.