ClawHub

Qwen Image Edit

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Qwen/Alibaba Cloud image generation and editing helper, with the main user consideration being that prompts and supplied images are sent to a third-party API.

Install only if you are comfortable using Alibaba Cloud DashScope for image generation/editing. Treat prompts, local images, and image URLs you provide as data sent to that service, and do not use private, confidential, or regulated images unless that matches your own privacy and compliance expectations.

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 (3)

Vague Triggers

Medium
Confidence
75% confidence
Finding
The trigger phrases are very broad and overlap with common requests such as generating or editing images, which can cause the skill to activate in contexts the user did not explicitly intend. Overbroad activation increases the chance that user content is routed to an external service without informed consent.

Vague Triggers

Medium
Confidence
70% confidence
Finding
The repeated bilingual invocation description remains ambiguous about when the skill should engage, reinforcing the same broad activation problem. Ambiguous boundaries are more dangerous here because the skill can send prompts and images to a third-party API.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The workflow explicitly instructs passing local images or image URLs to an external API, but it does not require a user-facing warning or consent about privacy and data transfer. Users may unknowingly upload sensitive local files, private URLs, or proprietary imagery to a third-party cloud service.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal