ClawHub
Back to skill

Security audit

Alibaba Cloud AI Text Qwen Generation

Security checks across malware telemetry and agentic risk

Overview

This is a conventional Alibaba Qwen helper that sends prompts to Alibaba Cloud when used and writes local request files, with no hidden or destructive behavior found.

Install this only if you intend to use Alibaba Cloud Model Studio. Use a scoped API key, expect prompts and request parameters to be sent to Alibaba Cloud, avoid sending secrets or regulated data unless approved for that provider, and review files written under output/aliyun-qwen-generation/ if prompts contain private content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill advertises behaviors that write files under output/ and send prompts to a remote Alibaba Cloud endpoint, but it does not declare permissions or clearly constrain those capabilities. Undeclared network and file-write behavior weakens user consent and policy enforcement because the skill can exfiltrate supplied content and persist artifacts without an explicit capability contract.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill includes a ready-to-use example that sends user prompts and system content to a remote model endpoint, but it does not prominently warn that prompt contents leave the local environment and may be processed by a third party. In a broad text-generation skill, that omission is risky because users may pass secrets, proprietary data, or regulated content assuming local handling.

External Transmission

Medium
Category
Data Exfiltration
Content
## Quick start (OpenAI-compatible endpoint)

```bash
curl -sS https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
  -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
96% confidence
Finding
curl -sS https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \ -H "Authorization: Bearer $DASHSCOPE_API_KEY" \ -H "Content-Type: application/json" \ -d

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.