ClawHub
Back to skill

Security audit

Qwen Video Generator

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward video-generation skill that sends prompts to Alibaba Cloud DashScope and saves the resulting video locally.

Install only if you are comfortable sending video prompts to Alibaba Cloud DashScope using your configured API key. Avoid confidential, personal, regulated, or secret content in prompts unless that external processing is approved, and choose a controlled output directory for generated MP4 files.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill documentation indicates capabilities to read environment variables, invoke shell commands, and access the network, but it does not declare permissions explicitly. This creates a transparency and governance gap: users and hosting platforms may not understand that API keys will be read from the environment and sent to an external service, increasing the risk of over-privileged execution or accidental secret exposure. In this context, network and env access are expected for a video-generation skill, which lowers suspicion of maliciousness, but the lack of declared permissions is still a real security issue.

Vague Triggers

Medium
Confidence
78% confidence
Finding
The activation criteria include broad phrases like '生成视频', 'AI视频', and 'text to video', which can overlap with many ordinary user requests. Overly broad triggering can cause the skill to activate unexpectedly, sending user prompts to an external video-generation service or causing unnecessary tool use without sufficiently clear user intent. Because the skill’s purpose is aligned with those phrases, this appears more like an overbroad design issue than malicious behavior, but it still increases the chance of unintended data disclosure or tool invocation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.