ClawHub

china-video-gen

Security checks across malware telemetry and agentic risk

Overview

This is a coherent instruction-only video generation skill, but users should be aware it uses external AI services and saves generated media locally.

Install only if you are comfortable sending video prompts, scripts, and narration to SiliconFlow through the dependent skills. Use a limited or monitored API key, install ffmpeg from trusted sources, review china-image-gen and china-tts separately, and delete generated assets if they contain private or business-sensitive material.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are very broad and overlap with ordinary user requests to create or convert content into videos, which increases the chance the skill activates in situations where the user did not explicitly intend to invoke this external-service workflow. Because the skill can generate media, use API-backed services, and produce files automatically, over-broad triggering raises the risk of unintended data transmission and unintended action execution.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the user to configure an API key and later routes user-provided prompts/content through external image and TTS services, but it does not clearly warn upfront that content will be transmitted to third-party providers. This can lead to users unknowingly sending sensitive business, personal, or proprietary material to external services, creating privacy, compliance, and consent issues.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal