Ai To Video

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

Overview

This AI video skill is mostly purpose-aligned, but it can automatically create a remote session and route broad user input to an external video service without a clear consent step.

Review before installing. Use this only if you are comfortable sending prompts, uploaded files, URLs, and generated video state to NemoVideo's remote API. Avoid confidential documents or private media unless you trust that service's data handling, and consider requiring the agent to ask before creating a token/session, uploading content, or starting generation.

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 (3)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The starter prompts are very generic (for example, 'convert my text or prompts' and 'turn this blog post intro into'), which can cause the skill to activate on ordinary conversation or partial user text that was not meant to invoke this capability. Because this skill uploads content to a remote service and performs network actions automatically, unintended activation can lead to accidental disclosure of user-provided content and unexpected external API usage.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The routing rule sends 'Everything else' to the SSE generation path, creating an overly broad catch-all that can interpret unrelated user messages as commands to the remote video backend. In this context, broad routing is more dangerous because the skill automatically establishes sessions and forwards user text to external infrastructure, increasing the chance of unintended data transmission and resource consumption.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The description markets the feature as seamless but does not clearly warn users that uploaded files, URLs, and prompts are transmitted to remote services for processing. Since the skill handles potentially sensitive documents and performs server-side rendering, missing disclosure can cause users to share confidential data without informed consent.

VirusTotal

66/66 vendors flagged this skill as clean.