CalvinBackup/CyberStrikeAI
1
0
Fork 0
mirror of https://github.com/Ed1s0nZ/CyberStrikeAI.git synced 2026-03-31 00:09:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
公明
2026-01-08 22:54:36 +08:00
committed by GitHub
parent 3043232937
commit dccbb80fa4
3 changed files with 275 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
README.md
View File

@@ -65,35 +65,40 @@ CyberStrikeAI ships with 100+ curated tools covering the whole kill chain:
## Basic Usage
### Quick Start
1. **Clone & install**
```bash
git clone https://github.com/Ed1s0nZ/CyberStrikeAI.git
cd CyberStrikeAI-main
go mod download
```
2. **Set up the Python tooling stack (required for the YAML tools directory)**
A large portion of `tools/*.yaml` recipes wrap Python utilities (`api-fuzzer`, `http-framework-test`, `install-python-package`, etc.). Create the project-local virtual environment once and install the shared dependencies:
```bash
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```
The helper tools automatically detect this `venv` (or any already active `$VIRTUAL_ENV`), so the default `env_name` works out of the box unless you intentionally supply another target.
3. **Configure OpenAI-compatible access**
Either open the in-app `Settings` panel after launch or edit `config.yaml`:
```yaml
openai:
api_key: "sk-your-key"
base_url: "https://api.openai.com/v1"
model: "gpt-4o"
auth:
password: "" # empty = auto-generate & log once
session_duration_hours: 12
security:
tools_dir: "tools"
```
4. **Install the tooling you need (optional)**
### Quick Start (One-Command Deployment)
**Prerequisites:**
- Go 1.21+ ([Install](https://go.dev/dl/))
- Python 3.10+ ([Install](https://www.python.org/downloads/))
**One-Command Deployment:**
```bash
git clone https://github.com/Ed1s0nZ/CyberStrikeAI.git
cd CyberStrikeAI-main
chmod +x run.sh && ./run.sh
```
The `run.sh` script will automatically:
- ✅ Check and validate Go & Python environments
- ✅ Create Python virtual environment
- ✅ Install Python dependencies
- ✅ Download Go dependencies
- ✅ Build the project
- ✅ Start the server
**First-Time Configuration:**
1. **Configure OpenAI-compatible API** (required before first use)
- Open http://localhost:8080 after launch
- Go to `Settings` → Fill in your API credentials:
```yaml
openai:
api_key: "sk-your-key"
base_url: "https://api.openai.com/v1" # or https://api.deepseek.com/v1
model: "gpt-4o" # or deepseek-chat, claude-3-opus, etc.
```
- Or edit `config.yaml` directly before launching
2. **Login** - Use the auto-generated password shown in the console (or set `auth.password` in `config.yaml`)
3. **Install security tools (optional)** - Install tools as needed:
```bash
# macOS
brew install nmap sqlmap nuclei httpx gobuster feroxbuster subfinder amass
@@ -101,15 +106,18 @@ CyberStrikeAI ships with 100+ curated tools covering the whole kill chain:
sudo apt-get install nmap sqlmap nuclei httpx gobuster feroxbuster
```
AI automatically falls back to alternatives when a tool is missing.
5. **Launch**
```bash
chmod +x run.sh && ./run.sh
# or
go run cmd/server/main.go
# or
go build -o cyberstrike-ai cmd/server/main.go
```
6. **Open the console** at http://localhost:8080, log in with the generated password, and start chatting.
**Alternative Launch Methods:**
```bash
# Direct Go run (requires manual setup)
go run cmd/server/main.go
# Manual build
go build -o cyberstrike-ai cmd/server/main.go
./cyberstrike-ai
```
**Note:** The Python virtual environment (`venv/`) is automatically created and managed by `run.sh`. Tools that require Python (like `api-fuzzer`, `http-framework-test`, etc.) will automatically use this environment.
### Core Workflows
- **Conversation testing** – Natural-language prompts trigger toolchains with streaming SSE output.

84
README_CN.md
View File

@@ -64,35 +64,40 @@ CyberStrikeAI 是一款 **AI 原生安全测试平台**，基于 Go 构建，集
## 基础使用
### 快速上手
1. **获取代码并安装依赖**
```bash
git clone https://github.com/Ed1s0nZ/CyberStrikeAI.git
cd CyberStrikeAI-main
go mod download
```
2. **初始化 Python 虚拟环境（tools 目录所需）**
`tools/*.yaml` 中大量工具（如 `api-fuzzer`、`http-framework-test`、`install-python-package` 等）依赖 Python 生态。首次进入项目根目录时请创建本地虚拟环境并安装依赖：
```bash
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
```
两个 Python 专用工具（`install-python-package` 与 `execute-python-script`）会自动检测该 `venv`（或已经激活的 `$VIRTUAL_ENV`），因此默认 `env_name` 即可满足大多数场景。
3. **配置模型与鉴权**
启动后在 Web 端 `Settings` 填写，或直接编辑 `config.yaml`：
```yaml
openai:
api_key: "sk-your-key"
base_url: "https://api.openai.com/v1"
model: "gpt-4o"
auth:
password: "" # 为空则首次启动自动生成强口令
session_duration_hours: 12
security:
tools_dir: "tools"
```
4. **按需安装安全工具（可选）**
### 快速上手（一条命令部署）
**环境要求：**
- Go 1.21+ ([下载安装](https://go.dev/dl/))
- Python 3.10+ ([下载安装](https://www.python.org/downloads/))
**一条命令部署：**
```bash
git clone https://github.com/Ed1s0nZ/CyberStrikeAI.git
cd CyberStrikeAI-main
chmod +x run.sh && ./run.sh
```
`run.sh` 脚本会自动完成：
- ✅ 检查并验证 Go 和 Python 环境
- ✅ 创建 Python 虚拟环境
- ✅ 安装 Python 依赖包
- ✅ 下载 Go 依赖模块
- ✅ 编译构建项目
- ✅ 启动服务器
**首次配置：**
1. **配置 AI 模型 API**（首次使用前必填）
- 启动后访问 http://localhost:8080
- 进入 `设置` → 填写 API 配置信息：
```yaml
openai:
api_key: "sk-your-key"
base_url: "https://api.openai.com/v1" # 或 https://api.deepseek.com/v1
model: "gpt-4o" # 或 deepseek-chat, claude-3-opus 等
```
- 或启动前直接编辑 `config.yaml` 文件
2. **登录系统** - 使用控制台显示的自动生成密码（或在 `config.yaml` 中设置 `auth.password`）
3. **安装安全工具（可选）** - 按需安装所需工具：
```bash
# macOS
brew install nmap sqlmap nuclei httpx gobuster feroxbuster subfinder amass
@@ -100,15 +105,18 @@ CyberStrikeAI 是一款 **AI 原生安全测试平台**，基于 Go 构建，集
sudo apt-get install nmap sqlmap nuclei httpx gobuster feroxbuster
```
未安装的工具会自动跳过或改用替代方案。
5. **启动服务**
```bash
chmod +x run.sh && ./run.sh
# 或
go run cmd/server/main.go
# 或
go build -o cyberstrike-ai cmd/server/main.go
```
6. **浏览器访问** http://localhost:8080 ，使用日志中提示的密码登录并开始对话。
**其他启动方式：**
```bash
# 直接运行（需手动配置环境）
go run cmd/server/main.go
# 手动编译
go build -o cyberstrike-ai cmd/server/main.go
./cyberstrike-ai
```
**说明：** Python 虚拟环境（`venv/`）由 `run.sh` 自动创建和管理。需要 Python 的工具（如 `api-fuzzer`、`http-framework-test` 等）会自动使用该环境。
### 常用流程
- **对话测试**：自然语言触发多步工具编排，SSE 实时输出。

220
run.sh
View File

@@ -2,59 +2,205 @@
set -euo pipefail
# CyberStrikeAI 启动脚本
# CyberStrikeAI 一键部署启动脚本
ROOT_DIR="$(cd "$(dirname "$0")" && pwd)"
cd "$ROOT_DIR"
echo "🚀 启动 CyberStrikeAI..."
# 颜色定义
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color
# 打印带颜色的消息
info() { echo -e "${BLUE}ℹ️ $1${NC}"; }
success() { echo -e "${GREEN}✅ $1${NC}"; }
warning() { echo -e "${YELLOW}⚠️ $1${NC}"; }
error() { echo -e "${RED}❌ $1${NC}"; }
echo ""
echo "=========================================="
echo " CyberStrikeAI 一键部署启动脚本"
echo "=========================================="
echo ""
CONFIG_FILE="$ROOT_DIR/config.yaml"
VENV_DIR="$ROOT_DIR/venv"
REQUIREMENTS_FILE="$ROOT_DIR/requirements.txt"
BINARY_NAME="cyberstrike-ai"
# 检查配置文件
if [ ! -f "$CONFIG_FILE" ]; then
echo "❌ 配置文件 config.yaml 不存在"
error "配置文件 config.yaml 不存在"
info "请确保在项目根目录运行此脚本"
exit 1
fi
# 检查 Python 环境
if ! command -v python3 >/dev/null 2>&1; then
echo "❌ 未找到 python3，请先安装 Python 3.10+"
exit 1
fi
# 检查并安装 Python 环境
check_python() {
if ! command -v python3 >/dev/null 2>&1; then
error "未找到 python3"
echo ""
info "请先安装 Python 3.10 或更高版本："
echo " macOS: brew install python3"
echo " Ubuntu: sudo apt-get install python3 python3-venv"
echo " CentOS: sudo yum install python3 python3-pip"
exit 1
fi
PYTHON_VERSION=$(python3 --version 2>&1 | awk '{print $2}')
PYTHON_MAJOR=$(echo "$PYTHON_VERSION" | cut -d. -f1)
PYTHON_MINOR=$(echo "$PYTHON_VERSION" | cut -d. -f2)
if [ "$PYTHON_MAJOR" -lt 3 ] || ([ "$PYTHON_MAJOR" -eq 3 ] && [ "$PYTHON_MINOR" -lt 10 ]); then
error "Python 版本过低: $PYTHON_VERSION (需要 3.10+)"
exit 1
fi
success "Python 环境检查通过: $PYTHON_VERSION"
}
# 创建并激活虚拟环境
if [ ! -d "$VENV_DIR" ]; then
echo "🐍 创建 Python 虚拟环境..."
python3 -m venv "$VENV_DIR"
fi
# 检查并安装 Go 环境
check_go() {
if ! command -v go >/dev/null 2>&1; then
error "未找到 Go"
echo ""
info "请先安装 Go 1.21 或更高版本："
echo " macOS: brew install go"
echo " Ubuntu: sudo apt-get install golang-go"
echo " CentOS: sudo yum install golang"
echo " 或访问: https://go.dev/dl/"
exit 1
fi
GO_VERSION=$(go version | awk '{print $3}' | sed 's/go//')
GO_MAJOR=$(echo "$GO_VERSION" | cut -d. -f1)
GO_MINOR=$(echo "$GO_VERSION" | cut -d. -f2)
if [ "$GO_MAJOR" -lt 1 ] || ([ "$GO_MAJOR" -eq 1 ] && [ "$GO_MINOR" -lt 21 ]); then
error "Go 版本过低: $GO_VERSION (需要 1.21+)"
exit 1
fi
success "Go 环境检查通过: $(go version)"
}
echo "🐍 激活虚拟环境..."
# shellcheck disable=SC1091
source "$VENV_DIR/bin/activate"
# 设置 Python 虚拟环境
setup_python_env() {
if [ ! -d "$VENV_DIR" ]; then
info "创建 Python 虚拟环境..."
python3 -m venv "$VENV_DIR"
success "虚拟环境创建完成"
else
info "Python 虚拟环境已存在"
fi
info "激活虚拟环境..."
# shellcheck disable=SC1091
source "$VENV_DIR/bin/activate"
if [ -f "$REQUIREMENTS_FILE" ]; then
info "安装/更新 Python 依赖..."
pip install --quiet --upgrade pip >/dev/null 2>&1 || true
# 尝试安装依赖，捕获错误输出
PIP_LOG=$(mktemp)
if pip install -r "$REQUIREMENTS_FILE" >"$PIP_LOG" 2>&1; then
success "Python 依赖安装完成"
else
# 检查是否是 angr 安装失败（需要 Rust）
if grep -q "angr" "$PIP_LOG" && grep -q "Rust compiler\|can't find Rust" "$PIP_LOG"; then
warning "angr 安装失败（需要 Rust 编译器）"
echo ""
info "angr 是可选依赖，主要用于二进制分析工具"
info "如果需要使用 angr，请先安装 Rust："
echo " macOS: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh"
echo " Ubuntu: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh"
echo " 或访问: https://rustup.rs/"
echo ""
info "其他依赖已安装，可以继续使用（部分工具可能不可用）"
else
warning "部分 Python 依赖安装失败，但可以继续尝试运行"
warning "如果遇到问题，请检查错误信息并手动安装缺失的依赖"
# 显示最后几行错误信息
echo ""
info "错误详情（最后 10 行）："
tail -n 10 "$PIP_LOG" | sed 's/^/ /'
echo ""
fi
fi
rm -f "$PIP_LOG"
else
warning "未找到 requirements.txt，跳过 Python 依赖安装"
fi
}
if [ -f "$REQUIREMENTS_FILE" ]; then
echo "📦 安装/更新 Python 依赖..."
pip install -r "$REQUIREMENTS_FILE"
else
echo "⚠️ 未找到 requirements.txt，跳过 Python 依赖安装"
fi
# 构建 Go 项目
build_go_project() {
info "下载 Go 依赖..."
go mod download >/dev/null 2>&1 || {
error "Go 依赖下载失败"
exit 1
}
info "构建项目..."
if go build -o "$BINARY_NAME" cmd/server/main.go 2>&1; then
success "项目构建完成: $BINARY_NAME"
else
error "项目构建失败"
exit 1
fi
}
# 检查 Go 环境
if ! command -v go >/dev/null 2>&1; then
echo "❌ Go 未安装，请先安装 Go 1.21 或更高版本"
exit 1
fi
# 检查是否需要重新构建
need_rebuild() {
if [ ! -f "$BINARY_NAME" ]; then
return 0 # 需要构建
fi
# 检查源代码是否有更新
if [ "$BINARY_NAME" -ot cmd/server/main.go ] || \
[ "$BINARY_NAME" -ot go.mod ] || \
find internal cmd -name "*.go" -newer "$BINARY_NAME" 2>/dev/null | grep -q .; then
return 0 # 需要重新构建
fi
return 1 # 不需要构建
}
# 下载依赖
echo "📦 下载 Go 依赖..."
go mod download
# 主流程
main() {
# 环境检查
info "检查运行环境..."
check_python
check_go
echo ""
# 设置 Python 环境
info "设置 Python 环境..."
setup_python_env
echo ""
# 构建 Go 项目
if need_rebuild; then
info "准备构建项目..."
build_go_project
else
success "可执行文件已是最新，跳过构建"
fi
echo ""
# 启动服务器
success "所有准备工作完成！"
echo ""
info "启动 CyberStrikeAI 服务器..."
echo "=========================================="
echo ""
# 运行服务器
exec "./$BINARY_NAME"
}
# 构建项目
echo "🔨 构建项目..."
go build -o cyberstrike-ai cmd/server/main.go
# 运行服务器
echo "✅ 启动服务器..."
./cyberstrike-ai
# 执行主流程
main