Free Video Music

• Outcome: Pass
• Latest audit: May 29, 2026, 8:43 PM
• Version:
  1.0.0

Overview

This is a disclosed cloud video/music editing skill that sends selected media and prompts to NemoVideo for processing, with no evidence of hidden or destructive behavior.

Install only if you are comfortable sending chosen videos, media URLs, audio/images, edit prompts, and related session metadata to NemoVideo for cloud processing. Prefer a dedicated NEMO_TOKEN, avoid confidential footage unless you trust the provider, and keep prompts within the video-editing task so unrelated text is not routed to the remote backend.

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: 93% confidence
• Finding: The manifest presents the skill as a narrow 'add music to videos' tool, but the body exposes a materially broader remote video editing surface including uploads, timeline manipulation, text overlays, aspect-ratio handling, exports, and multi-format media processing. This mismatch can mislead users and reviewers about what data and capabilities are actually invoked, increasing the chance of unauthorized or unexpected processing through the third-party service.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The catch-all route sends essentially any unmatched request to the SSE/chat backend, which can cause unrelated user prompts or sensitive free-form text to be forwarded to a third-party service without clear user intent. In a skill advertised for one narrow task, this broad trigger increases the risk of over-collection, accidental activation, and unintended remote actions.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the agent to connect to a third-party cloud API and upload user videos/prompts, but the user-facing description does not prominently warn that content is sent off-platform for remote processing. This creates a privacy and consent problem because users may share personal or proprietary media believing processing is local or limited.

VirusTotal

65/65 vendors flagged this skill as clean.