Text To Ai Video Generator Free

• Outcome: Review
• Latest audit: May 29, 2026, 9:32 PM
• Version:
  1.0.0

Overview

This skill is a cloud media-generation workflow that can upload user prompts and files to a third-party backend, with broad routing and limited user-facing disclosure.

Install only if you are comfortable sending prompts and uploaded files to the NemoVideo cloud service. Avoid private, confidential, regulated, or copyrighted source files unless you have checked the provider’s retention and terms. Use a dedicated token, monitor credit/session activity, and prefer explicit confirmation before uploads, edits, exports, or long-running render jobs.

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 (5)

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The skill is presented as a text-to-video generator, but the documented supported formats and upload pipeline extend to generic media types including video, audio, and images. This creates a scope mismatch that can mislead users about what data may be transmitted to the third-party backend and enables broader data handling than the stated purpose justifies.

Context-Inappropriate Capability

Medium

• Confidence: 88% confidence
• Finding: The skill exposes generic upload, session-state inspection, and editing/export capabilities that go beyond a narrowly scoped text-to-video workflow. Broad capabilities increase the chance of unnecessary data access and make it easier for the skill to be invoked for unrelated content manipulation tasks, expanding privacy and misuse risk.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The invocation examples are broad and generic enough that the skill may activate on common requests about generating, editing, or exporting content. Over-broad triggering can cause accidental routing of user prompts and unintended transmission of user content to the remote backend without sufficiently specific user intent.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The catch-all rule routes 'Everything else' to the SSE backend, which is overly permissive and can forward ambiguous user inputs to a third-party service. In a skill that accepts user content and cloud processing, such broad routing materially increases the risk of unintended data disclosure and misuse.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill instructs the agent to connect to a cloud backend, create tokens, and maintain remote sessions, but it does not prominently warn users that their prompts/files may be uploaded and processed by a third-party service. This is a real privacy and transparency issue, especially because the skill supports large file uploads and persistent session state.

VirusTotal

63/63 vendors flagged this skill as clean.