Video Generator Generator

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

Overview

This cloud video-generation skill is purpose-aligned, but it can automatically create remote sessions and broadly forward user text or files to a third-party backend without clear opt-in.

Install only if you are comfortable sending prompts, scripts, media files, and generated project state to nemovideo.ai. Use explicit commands for video generation, avoid sensitive or proprietary content, and ask the agent to confirm before creating a token, starting a session, uploading files, or forwarding ambiguous text to the backend.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Context-Inappropriate Capability

Medium

• Confidence: 92% confidence
• Finding: The skill instructs the agent to automatically obtain anonymous tokens and create remote sessions on behalf of the user, which expands the skill from simple video generation into autonomous account/session provisioning against a third-party service. This can trigger unintended external actions, consume third-party resources, and create opaque authorization state without explicit user consent or clear trust boundaries.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The phrase inviting users to 'share your text prompts' is so broad that it could match ordinary conversation and cause the skill to activate when the user did not intend to use this capability. Over-broad invocation increases the chance of accidental uploads, remote API calls, or routing unrelated text into the external video-generation backend.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example trigger 'generate my text prompts' is vague and could overlap with many benign requests unrelated to this skill. Because the skill performs networked actions and may establish sessions automatically, ambiguous triggers materially increase the risk of unintended execution.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The catch-all rule routing 'everything else' to the SSE action is unsafe because it effectively forwards a wide range of unmatched user inputs to a remote backend. In this skill, that means ordinary or unrelated user text may be sent off-platform, increasing risks of data exfiltration, unintended edits, or unauthorized third-party processing.

VirusTotal

66/66 vendors flagged this skill as clean.