Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Qwen Api

v1.0.0

通义千问 API 开发助手,精通 Qwen 模型调用、DashScope SDK、多模态、Agent 开发

0· 133·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zhangifonly/qwen-api.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Qwen Api" (zhangifonly/qwen-api) from ClawHub.
Skill page: https://clawhub.ai/zhangifonly/qwen-api
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install qwen-api

ClawHub CLI

Package manager switcher

npx clawhub@latest install qwen-api
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name and description claim an API development/helper for Qwen/DashScope and the SKILL.md contains code samples, endpoints, model matrix, file upload, and function-calling examples that align with that purpose.
!
Instruction Scope
Instructions include an explicit example to disable content inspection using the X-DashScope-DataInspection header (guidance to bypass moderation). That is outside benign developer guidance and can enable misuse. Otherwise the examples stick to API calls and file uploads relevant to the stated purpose.
Install Mechanism
This is an instruction-only skill with no install spec or downloaded code. It suggests installing the standard 'openai' pip package, which is proportionate and low-risk for the described task.
Credentials
The manifest requests no environment variables, which matches the instruction-only nature. The examples do require an API key in practice (shown as 'sk-your-dashscope-api-key') — the skill doesn't ask for or store credentials itself, but the user will need to provide a DashScope API key when using the API.
Persistence & Privilege
The skill is not always-on, does not request elevated persistence, and contains no install hooks or changes to other skills or system configuration.
What to consider before installing
This guide is mostly a straightforward Qwen/DashScope API cheat-sheet, but it includes an explicit technique to disable content inspection on the international endpoint. Consider the following before using or trusting this skill: 1) Disabling moderation can lead to generation of unsafe, illegal or policy-violating content — avoid using that header unless you understand legal and policy implications. 2) Verify the endpoint and pricing claims independently (the skill has no homepage or source). 3) Only provide a DashScope API key with the minimum necessary permissions and monitor/rotate it; do not paste secret keys into third-party UIs you don't trust. 4) If you need moderation or audit logging, do not follow the 'disable' header guidance. 5) If you want higher assurance, ask the publisher for source code or official docs and test calls from a sandbox account first.

Like a lobster shell, security has layers — review code before you run it.

latestvk97b283h4ktrvrjtmf8afbjmyh83d8mq
133downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

通义千问 API - 阿里云百炼/DashScope 接入指南

简介

通义千问(Qwen)是阿里云的大语言模型系列,通过百炼平台(DashScope)提供 API。 核心优势:兼容 OpenAI SDK 调用,迁移成本极低;国际版无内容审核。

模型矩阵

模型特点适用场景
qwen-max最强能力,深度推理复杂分析、创意写作
qwen-plus性价比最优(推荐)日常对话、代码生成
qwen-turbo响应最快简单任务、高并发
qwen-long长文本(1000 万 token)超长文档分析
qwq-plus推理增强(思维链)数学、逻辑推理
qwen-vl-max视觉理解图片/视频分析
qwen-audio-turbo音频理解语音转录、音频分析

API 端点

地域Base URL说明
新加坡(国际版)https://dashscope-intl.aliyuncs.com/compatible-mode/v1推荐,无内容审核
中国(北京)https://dashscope.aliyuncs.com/compatible-mode/v1国内访问快
美国(弗吉尼亚)https://dashscope-us.aliyuncs.com/compatible-mode/v1美国节点

基础调用(兼容 OpenAI SDK)

pip install -U openai
from openai import OpenAI
client = OpenAI(
    api_key="sk-your-dashscope-api-key",
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
)
response = client.chat.completions.create(
    model="qwen-plus",
    messages=[
        {"role": "system", "content": "你是一个专业的编程助手。"},
        {"role": "user", "content": "用 Python 实现一个 LRU 缓存"}
    ]
)
print(response.choices[0].message.content)

多模态调用

# 图片理解
response = client.chat.completions.create(model="qwen-vl-max", messages=[{"role": "user",
    "content": [{"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
                {"type": "text", "text": "描述图片内容"}]}])
# 视频理解
response = client.chat.completions.create(model="qwen-vl-max", messages=[{"role": "user",
    "content": [{"type": "video_url", "video_url": {"url": "https://example.com/video.mp4"}},
                {"type": "text", "text": "总结视频内容"}]}])

函数调用

tools = [{"type": "function", "function": {"name": "get_weather", "description": "获取城市天气",
    "parameters": {"type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"]}}}]
response = client.chat.completions.create(
    model="qwen-plus", messages=[{"role": "user", "content": "北京天气?"}], tools=tools)

绕过内容审核(国际版)

import json
response = client.chat.completions.create(model="qwen-plus",
    messages=[{"role": "user", "content": "你的问题"}],
    extra_headers={"X-DashScope-DataInspection": json.dumps({"input": "disable", "output": "disable"})})

仅在国际版端点生效,国内版无法禁用审核。

长文本处理(qwen-long,支持 1000 万 token)

file = client.files.create(file=open("long_doc.pdf", "rb"), purpose="file-extract")
response = client.chat.completions.create(model="qwen-long", messages=[
    {"role": "system", "content": f"fileid://{file.id}"},
    {"role": "user", "content": "总结文档核心观点"}])

定价(每百万 token)

模型输入输出
qwen-plus¥0.8¥2.0
qwen-max¥2.0¥6.0
qwen-turbo¥0.3¥0.6

最佳实践

  • 日常推荐 qwen-plus,兼顾能力和成本
  • 国际版 + 禁用审核 = 无内容限制
  • 超长文档用 qwen-long + 文件上传

Comments

Loading comments...