ClawHub
Back to skill

Security audit

千问生图

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Qwen image-generation helper that calls Alibaba Cloud DashScope as disclosed, with no hidden persistence or unrelated behavior found.

Install only if you intend to use Alibaba Cloud DashScope for image generation. Prompts, negative prompts, and generation settings will be sent to DashScope and may incur API costs, so avoid putting secrets, personal data, or confidential material in image prompts.

SkillSpector

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
91% confidence
Finding
The activation description includes broad, everyday phrases such as '生成图片', '画图', and 'text-to-image', plus brand references, which can cause the skill to trigger in cases where the user did not explicitly intend to invoke this external image-generation capability. Unintended activation is security-relevant here because it may route user prompts to a third-party cloud API and incur cost or disclose sensitive prompt content without clear user intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents returning image URLs but does not warn that user prompts and parameters are transmitted to Alibaba Cloud's DashScope service. This omission can lead users to unknowingly send sensitive or regulated data to an external provider, making privacy, compliance, and consent risks materially higher in the context of a cloud-backed generation skill.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/api.md:15