# AI-Infra-Guard
**Repository Path**: xtu_hl/AI-Infra-Guard
## Basic Information
- **Project Name**: AI-Infra-Guard
- **Description**: 1
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-03-16
- **Last Updated**: 2025-03-16
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# 🛡️ AI基础设施安全评估系统
AI Infra Guard(AI Infrastructure Guard) 是一个**高效**、**轻量**、**易用**的AI基础设施安全评估工具,专为发现和检测AI系统潜在安全风险而设计。
## 🚀 快速预览
**WEBUI**

**命令行**


## 🚀 项目亮点
* **高效扫描**
* 支持 28 种 AI 框架指纹识别
* 涵盖 200+ 安全漏洞数据库
* **易于使用**
* 开箱即用,无复杂配置
* 指纹、漏洞YAML规则定义
* 灵活的匹配语法
* **轻量级**
* 核心组件简洁高效
* 二进制体积小,资源占用低
* 跨平台支持
## 📊 AI组件覆盖情况
| 组件名称 | 漏洞数量 |
|--------------------|------|
| anythingllm | 8 |
| langchain | 33 |
| Chuanhugpt | 0 |
| clickhouse | 22 |
| comfy_mtb | 1 |
| ComfyUI-Prompt-Preview | 1 |
| ComfyUI-Custom-Scripts | 1 |
| comfyui | 1 |
| dify | 11 |
| fastchat-webui | 0 |
| fastchat | 1 |
| feast | 0 |
| gradio | 42 |
| jupyterlab | 6 |
| jupyter-notebook | 1 |
| jupyter-server | 13 |
| kubeflow | 4 |
| kubepi | 5 |
| llamafactory | 1 |
| llmstudio | 0 |
| ollama | 7 |
| open-webui | 8 |
| pyload-ng | 18 |
| qanything | 2 |
| ragflow | 2 |
| ray | 4 |
| tensorboard | 0 |
| vllm | 4 |
| xinference | 0 |
| triton-inference-server | 7 |
## 📦 安装与使用
### 安装
下载地址: [https://github.com/Tencent/AI-Infra-Guard/releases](https://github.com/Tencent/AI-Infra-Guard/releases)
### 使用
**WEBUI 可视化操作**
```
./ai-infra-guard -ws
```
**本地一键检测**
```
./ai-infra-guard -localscan
```
**单个目标**
```
./ai-infra-guard -target [IP/域名]
```
**多个目标**
```
./ai-infra-guard -target [IP/域名] -target [IP/域名]
```
**从文件读取**
```
./ai-infra-guard -file target.txt
```
**AI分析**
```
# hunyuan token
./ai-infra-guard -target [IP/Domain] -ai -hunyuan-token [Hunyuan token]
# deepseek token
./ai-infra-guard -target [IP/Domain] -ai -deepseek-token [Deepseek token]
```
## 🔍 指纹匹配规则
AI Infra Guard 基于WEB指纹识别组件,指纹规则在[data/fingerprints](./data/fingerprints)目录中,漏洞匹配规则在[data/vuln](./data/vuln)目录中。
### 示例:Gradio 指纹规则
```yaml
info:
name: gradio
author: Security Team
severity: info
metadata:
product: gradio
vendor: gradio
http:
- method: GET
path: '/'
matchers:
- body="