To No Generator

• Outcome: Review
• Latest audit: May 29, 2026 at 9:39 PM UTC
• Version:
  1.0.0

Overview

This is a coherent cloud video-generation skill, but it routes very broad user input to an external service and obtains a temporary service token with limited upfront user control.

Install only if you are comfortable sending prompts and uploaded documents or media to NemoVideo for processing. Use explicit requests, avoid confidential files, and consider asking the agent to confirm before uploading files or starting generation/export.

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 (4)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger guidance uses generic phrases like "generate my text or script" and "generate a video from this text," which are broad enough to match ordinary conversation rather than an explicit invocation of this skill. Because the skill can upload content and send prompts to a remote backend, accidental activation could cause unintended transmission of user data or kick off cloud actions without clear user intent.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The routing table sends "Everything else" to the SSE action, effectively making the skill a catch-all for a very large set of prompts. In this skill, that means arbitrary user text may be forwarded to an external service, greatly increasing the chance of unintended activation, privacy leakage, and unauthorized cloud-side processing.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill description says it handles AI video generation on cloud GPUs, but it does not clearly warn users up front that their prompts and uploaded files are sent to a third-party cloud backend for processing. Users may disclose sensitive text, documents, PDFs, or videos without informed consent, creating privacy and compliance risk.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The setup flow silently acquires an anonymous token and binds subsequent actions to that session, but the user is not clearly informed that a token will be obtained and used on their behalf. While lower impact than direct data exfiltration, this weakens transparency and can surprise users about account/session creation and backend tracking.

VirusTotal

62/62 vendors flagged this skill as clean.