Ai Animation 3d Model

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

Overview

This is a cloud 3D-animation skill, but it asks agents to automatically connect to a third-party service and has broad routing and upload behavior that users should review first.

Install only if you are comfortable sending 3D assets, prompts, URLs, and render metadata to the nemovideo.ai cloud service. Use explicit 3D animation/export requests, avoid confidential models unless you have reviewed the provider's privacy and retention terms, and be cautious with URL uploads because the skill does not document clear fetch restrictions.

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 (4)

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: The skill is presented as a 3D model animation tool, but the documentation exposes a broader media editing and rendering pipeline including text overlays, audio tracks, exports in many formats, timeline manipulation, and GUI-to-API translation. This capability expansion can cause the agent to perform actions beyond the user's likely expectation and increases the chance of unintended remote processing or data handling outside the declared scope.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: Allowing uploads by arbitrary remote URL introduces an SSRF-like fetch primitive through the backend, enabling the skill to cause the remote service to retrieve attacker-chosen resources. Even if the fetch occurs server-side, it can be abused to access internal-only endpoints, private media, or unexpected third-party content, and it is unjustified for a skill whose primary function is animating user-supplied 3D models.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger guidance includes a very broad phrase ('tell me what you're thinking') that can match ordinary conversation rather than an intentional request to animate a 3D model. Overbroad activation increases the risk of accidental invocation, causing unintended cloud setup, token acquisition, session creation, or file-handling behaviors without sufficiently clear user intent.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill instructs the agent to connect automatically to a cloud backend, acquire an anonymous token, and create a remote session, but it does not clearly warn the user that uploaded files and prompts will be sent to a third-party cloud service. This undermines informed consent and may expose sensitive or proprietary 3D assets to external processing without adequate disclosure.

VirusTotal

64/64 vendors flagged this skill as clean.