Video Generation Generator

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:43 PM UTC
• Version:
  1.0.0

Overview

This is a cloud video-generation skill whose network use, uploads, token handling, and export workflow fit its stated purpose, with privacy and scope caveats users should understand.

Install or invoke this only for video-generation work and only with prompts, files, and URLs you are comfortable sending to NemoVideo's cloud service. Keep NEMO_TOKEN private, avoid confidential or rights-sensitive media unless you trust the provider, and treat broad or ambiguous requests as something to confirm before sending.

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
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The manifest advertises a narrow set of supported formats and local files, but the body documents many more file types plus remote URL ingestion. That mismatch can mislead users and downstream tooling about what data the skill may accept and transmit, increasing the chance of unexpected handling of sensitive or untrusted content.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The routing rule sends 'everything else' to the SSE action, which is so broad that unrelated user requests could be captured and forwarded to the remote backend. This creates a prompt-routing and privacy risk because arbitrary user text may be transmitted off-platform without clear relevance or consent.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The getting-started text does not clearly warn users that prompts, files, and session state are transmitted to external APIs and processed on cloud infrastructure. Users may disclose sensitive content believing the action is local or agent-internal when it is actually sent to a third party.

Missing User Warnings

Low

• Confidence: 86% confidence
• Finding: The metadata declares use of a local environment variable and config path, but the skill does not clearly disclose that it may read local credentials/configuration to authenticate. While common, undisclosed use of local auth material can surprise users and reduces transparency around what local data the skill depends on.

VirusTotal

63/63 vendors flagged this skill as clean.