usestrix / strix

Strix: The open-source AI pentesting tool. Strix：开源 AI 渗透测试工具。

Autonomous AI hackers that find and fix your app’s vulnerabilities. 自主 AI 黑客，能够发现并修复你应用程序中的漏洞。

Tip: New! Strix integrates seamlessly with GitHub Actions and CI/CD pipelines. Automatically scan for vulnerabilities on every pull request and block insecure code before it reaches production - Get started with no setup required. 提示：新功能！Strix 可与 GitHub Actions 和 CI/CD 流水线无缝集成。在每次 Pull Request 时自动扫描漏洞，并在不安全代码进入生产环境前将其拦截——无需任何配置即可开始使用。

Strix Overview: Strix are autonomous AI penetration testing agents that act just like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proof-of-concepts. Built for developers and security teams who need fast, accurate security testing without the overhead of manual pentesting or the false positives of static analysis tools. Strix 概述：Strix 是自主 AI 渗透测试代理，其行为与真正的黑客无异——它们动态运行你的代码，发现漏洞，并通过实际的概念验证（PoC）进行验证。专为需要快速、准确安全测试的开发人员和安全团队打造，无需手动渗透测试的繁琐开销，也避免了静态分析工具带来的误报。

Key Capabilities: 核心功能：

• Full pentesting toolkit - reconnaissance, exploitation, and validation out of the box 完整的渗透测试工具包——开箱即用的侦察、利用和验证功能。
• Multi-agent orchestration - teams of AI pentesters that collaborate and scale 多代理编排——可协作并扩展的 AI 渗透测试团队。
• Real exploit validation - working PoCs, not false positives like legacy vulnerability scanners 真实的漏洞利用验证——提供可运行的 PoC，而非传统漏洞扫描器那样的误报。
• Developer‑first CLI - actionable findings with remediation guidance 开发者优先的 CLI——提供带有修复指导的可操作性发现结果。
• Auto-fix & reporting - generate patches and compliance-ready pentest reports 自动修复与报告——生成补丁及符合合规要求的渗透测试报告。

Use Cases 应用场景

• Application Security Testing - Detect and validate critical vulnerabilities in your applications 应用程序安全测试——检测并验证应用程序中的关键漏洞。
• Rapid Penetration Testing - Get penetration tests done in hours, not weeks, with compliance reports 快速渗透测试——在数小时（而非数周）内完成渗透测试，并获取合规报告。
• Bug Bounty Automation - Automate bug bounty research and generate PoCs for faster reporting 漏洞赏金自动化——自动化漏洞赏金研究并生成 PoC，以实现更快的报告提交。
• CI/CD Integration - Run tests in CI/CD to block vulnerabilities before reaching production CI/CD 集成——在 CI/CD 中运行测试，在代码进入生产环境前拦截漏洞。

🚀 Quick Start 🚀 快速开始

Prerequisites: 先决条件：

• Docker (running) Docker（运行中）
• An LLM API key from any supported provider (OpenAI, Anthropic, Google, etc.) 来自任何受支持提供商（OpenAI、Anthropic、Google 等）的 LLM API 密钥。

Installation & First Scan 安装与首次扫描

# Install Strix
curl -sSL https://strix.ai/install | bash

# Configure your AI provider
export STRIX_LLM="openai/gpt-5.4"
export LLM_API_KEY="your-api-key"

# Run your first security assessment
strix --target ./app-directory

Note: First run automatically pulls the sandbox Docker image. Results are saved to strix_runs/ 注意：首次运行时会自动拉取沙箱 Docker 镜像。结果将保存至 strix_runs/<run-name>。

☁️ Strix Platform ☁️ Strix 平台

Try the Strix full-stack penetration testing platform at app.strix.ai - sign up for free, connect your repos and domains, and launch a pentest in minutes. 访问 app.strix.ai 体验 Strix 全栈渗透测试平台——免费注册，连接你的仓库和域名，几分钟内即可启动渗透测试。

• Validated findings with PoCs - every vulnerability includes a working proof-of-concept exploit and reproduction steps 经验证的发现结果与 PoC——每个漏洞都包含可运行的概念验证利用程序和复现步骤。
• One-click autofix - AI-generated security patches as ready-to-merge pull requests 一键自动修复——AI 生成的安全补丁，可直接作为 Pull Request 合并。
• Continuous pentesting - always-on vulnerability scanning that keeps pace with your deployments 持续渗透测试——始终在线的漏洞扫描，与你的部署进度保持同步。
• DevSecOps integrations - GitHub, GitLab, Bitbucket, Slack, Jira, Linear, and CI/CD pipelines DevSecOps 集成——支持 GitHub、GitLab、Bitbucket、Slack、Jira、Linear 和 CI/CD 流水线。
• Continuous learning - AI that builds on past findings, adapts to your codebase, and reduces false positives over time 持续学习——AI 基于过往发现进行构建，适应你的代码库，并随时间推移减少误报。

Start your first pentest → 开始你的第一次渗透测试 →

✨ Features ✨ 特性

Agentic Pentesting Tools: Strix agents come equipped with a comprehensive offensive security toolkit - the same tools used by professional penetration testers and ethical hackers: 代理式渗透测试工具：Strix 代理配备了全面的进攻性安全工具包——与专业渗透测试人员和白帽黑客使用的工具相同：

• HTTP Interception Proxy - Full request/response manipulation and analysis with Caido HTTP 拦截代理——通过 Caido 进行完整的请求/响应操作与分析。
• Browser Exploitation - Automated browser for testing XSS, CSRF, clickjacking, and auth bypass flows 浏览器利用——用于测试 XSS、CSRF、点击劫持和身份验证绕过流程的自动化浏览器。
• Shell & Command Execution - Interactive terminal for exploit development and post-exploitation Shell 与命令执行——用于漏洞利用开发和后渗透阶段的交互式终端。
• Custom Exploit Runtime - Python sandbox for writing and validating proof-of-concept exploits 自定义漏洞利用运行时——用于编写和验证概念验证漏洞利用程序的 Python 沙箱。
• Reconnaissance & OSINT - Automated attack surface mapping, subdomain enumeration, and fingerprinting 侦察与 OSINT——自动化的攻击面映射、子域名枚举和指纹识别。
• Static & Dynamic Code Analysis - SAST + DAST capabilities for comprehensive application security testing 静态与动态代码分析——SAST + DAST 功能，实现全面的应用程序安全测试。
• Vulnerability Knowledge Base - Structured findings with CVSS scoring and OWASP classification 漏洞知识库——带有 CVSS 评分和 OWASP 分类的结构化发现结果。

Comprehensive Vulnerability Scanner: Strix identifies, validates, and exploits a wide range of security vulnerabilities across the OWASP Top 10 and beyond: 全面的漏洞扫描器：Strix 可识别、验证并利用 OWASP Top 10 及其他范围内的广泛安全漏洞：

• Broken Access Control - IDOR, privilege escalation, auth bypass 失效的访问控制——IDOR、权限提升、身份验证绕过。
• Injection Attacks - SQL injection, NoSQL injection, OS command injection, SSTI 注入攻击——SQL 注入、NoSQL 注入、OS 命令注入、SSTI。
• Server-Side Vulnerabilities - SSRF, XXE, insecure deserialization, RCE 服务端漏洞——SSRF、XXE、不安全的反序列化、RCE。
• Client-Side Attacks - XSS (stored/reflected/DOM), prototype pollution, CSRF 客户端攻击——XSS（存储型/反射型/DOM 型）、原型污染、CSRF。
• Business Logic Flaws - Race conditions, payment manipulation, workflow bypass 业务逻辑缺陷——竞态条件、支付篡改、工作流绕过。
• Authentication & Session - JWT attacks, session fixation, credential stuffing vectors 身份验证与会话——JWT 攻击、会话固定、撞库向量。
• Infrastructure & Cloud - Misconfigurations, exposed services, cloud security issues 基础设施与云——配置错误、暴露的服务、云安全问题。
• API Security - Broken authentication, mass assignment, rate limiting bypass API 安全——失效的身份验证、大规模赋值、速率限制绕过。

Graph of Agents (Multi-Agent Pentesting): Advanced multi-agent orchestration for comprehensive automated penetration testing: 代理图谱（多代理渗透测试）：用于全面自动化渗透测试的高级多代理编排：

• Distributed Pentesting - Specialized AI agents for recon, exploitation, and post-exploitation 分布式渗透测试——用于侦察、利用和后渗透的专业 AI 代理。
• Scalable Security Testing - Parallel execution across multiple targets for fast, comprehensive coverage 可扩展的安全测试——跨多个目标并行执行，实现快速、全面的覆盖。
• Dynamic Coordination - Agents share discoveries, chain vulnerabilities, and collaborate like a red team 动态协调——代理共享发现结果、串联漏洞，并像红队一样协作。

Usage Examples 使用示例

# Basic Usage
# Scan a local codebase
strix --target ./app-directory

# Security review of a GitHub repository
strix --target https://github.com/org/repo

# Black-box web application assessment
strix --target https://your-app.com

# Advanced Testing Scenarios
# Grey-box authenticated testing
strix --target https://your-app.com --instruction "Perform authenticated testing using credentials: user:pass"

# Multi-target testing (source code + deployed app)
strix -t https://github.com/org/app -t https://your-app.com

# White-box source-aware scan (local repository)
strix --target ./app-directory --scan-mode standard

# Focused testing with custom instructions
strix --target api.your-app.com --instruction "Focus on business logic flaws and IDOR vulnerabilities"

# Provide detailed instructions through file (e.g., rules of engagement, scope, exclusions)
strix --target api.your-app.com --instruction-file ./instruction.md

# Force PR diff-scope against a specific base branch
strix -n --target ./ --scan-mode quick --scope-mode diff --diff-base origin/main

Headless Mode: Run Strix programmatically without interactive UI using the -n/—non-interactive flag - perfect for servers and automated jobs. The CLI prints real-time… 无头模式：使用 -n/--non-interactive 标志以编程方式运行 Strix，无需交互式 UI——非常适合服务器和自动化任务。CLI 会实时打印……