ClawHub

即梦AI视频生成

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Volcengine/Jimeng cloud video-generation skill, with privacy and cost considerations users should understand before use.

Install this only if you intend to use Volcengine/Jimeng cloud video generation. Avoid submitting confidential prompts, images, or regulated content unless you are comfortable sending it to Volcengine, and protect the configured API key because accidental or broad-triggered use may consume paid quota.

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 (4)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly shows prompts and generation requests being sent to a third-party API, but it does not clearly disclose the privacy and data-handling implications to users. This can cause users to unknowingly transmit sensitive prompts, images, or generated content metadata to an external provider, creating confidentiality and compliance risk.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrase at line 11 is broad enough to match generic user requests for video creation rather than requests specifically intended for this skill. This can cause unintended activation, routing users into a tool that consumes API-backed resources and may process prompts or media unexpectedly, increasing the risk of accidental data sharing or unnecessary cost-incurring actions.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list contains multiple generic phrases like '生成视频', 'AI视频', and '视频制作' without boundaries or exclusion rules, making overmatching likely. In an agent ecosystem, this can hijack broad classes of normal requests, causing unintended execution of an external API workflow that may spend credits, handle user media, or displace more appropriate skills.

External Transmission

Medium
Category
Data Exfiltration
Content
### 生成带声音的视频

```bash
curl -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${API_KEY}" \
  -d '{
Confidence
89% confidence
Finding
curl -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer ${API_KEY}" \ -d

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal