Video Editor Free Windows

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.0

Overview

This is a real cloud video-editing skill, but it connects to a third-party backend automatically and can forward broad user prompts without a clear opt-in boundary.

Review before installing. Use it only if you are comfortable sending media files, URLs, and editing prompts to NemoVideo's cloud service. Avoid confidential footage unless you trust that provider, and prefer a version that asks for explicit consent before token creation, session setup, uploads, or forwarding free-form prompts.

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 (4)

Description-Behavior Mismatch

Medium

• Confidence: 93% confidence
• Finding: The skill advertises support for only MP4, MOV, AVI, and WebM, but later documents acceptance of many additional file types including images and audio. This mismatch can cause users or calling systems to send data types they did not intend to expose, and weakens trust and policy enforcement based on the manifest description.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The startup prompt and invocation examples are broad enough that ordinary conversation like 'export' or 'edit my clips' could trigger the skill without strong user intent. In a skill that uploads media and connects to a remote backend, accidental activation increases the chance of unintended data transmission and unauthorized processing actions.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The catch-all rule routes 'everything else' to the SSE editing action, which is an overly permissive trigger for a remote-processing workflow. This means ambiguous or unrelated user text may be forwarded to the backend, potentially exposing user content or causing unintended edits and session activity.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the agent to automatically obtain a token and create a remote session on first open, while only telling the user 'Setting up...' and not clearly disclosing remote processing and data transmission. Because this skill handles personal media files, silent backend connection materially increases privacy risk and can surprise users with external account/session creation.

VirusTotal

64/64 vendors flagged this skill as clean.