AI驱动的漏洞赏金狩猎,尽在终端 - 侦察、20类漏洞、自主狩猎与报告生成。全部在Claude Code中完成。
AI 驱动的漏洞赏金狩猎——从侦察到报告,全在你的终端里。
发现漏洞。验证漏洞。获取报酬。无需订阅。
免费安装 · 快速开始 · 命令 · 它能发现什么 · 安装 · FAQ
这是你启动它时看到的画面。
██████ ██████ ██ ██ ██ ██ ███ █ ███████
██ ██ ██ ██ ██ ██ ██ ██ ████ █ ███
██████ ██████ ███████ ██ ██ ██ ██ █ ███
██████ ██████ ███████ ██ ██ ██ ███ ███
██ ██ ██ ██ ██ ██ ██ ██ ██ ██ ███
██████ ██████ ██ ██ ███████ ██ ██ ███
+ Recon. Hunt. Validate. Report. +
┌──────────────────────────────────────────────────────┐
│ Target target.com │
│ Mode full │
│ Output recon/target.com/ │
│ Auth session loaded │
└──────────────────────────────────────────────────────┘
● local Ready type /hunt to begin
bbhunter v4.3
一个专业的漏洞赏金狩猎工具包,无论是否订阅 Claude 均可使用。给它一个目标——它会处理侦察、测试漏洞,通过严格的门禁验证发现,并为 HackerOne、Bugcrowd、Intigriti 和 Immunefi 撰写可直接提交的报告。
它会记住一切。 在一个目标上发现的模式会用于下一个目标。会话会从上次中断的地方继续。
既可以作为 Claude Code 插件使用,也可以作为完全独立的 CLI(bughunter)使用,由免费 AI 提供商提供支持。
你不再需要 Claude Code、Claude Pro 或任何付费 AI 订阅。
安装一次,即可在你机器上的任何终端中使用 bughunter 命令:
git clone https://github.com/shuvonsec/claude-bug-bounty.git
cd claude-bug-bounty
./install.sh --agent standalone
bughunter help # show every command
bughunter setup # choose your AI provider (Ollama is free + offline)
bughunter recon target.com # map the attack surface
bughunter hunt target.com # hunt for vulnerabilities
bughunter validate "finding" # 7-Question Gate on your finding
bughunter report # write a submission-ready report
bughunter chat # interactive AI hunting shell
bughunter providers # list all available AI providers
bughunter status # check which provider is active
bughunter h target.com # short alias for hunt
bughunter r target.com # short alias for recon
bughunter v "finding" # short alias for validate
BugHunter 按以下顺序自动检测提供商:Ollama → Groq → DeepSeek → … → OpenRouter → Claude → OpenAI
随时切换提供商:bughunter setup
# 1. Install Ollama (runs AI locally, no internet needed after download)
curl -fsSL https://ollama.ai/install.sh | sh
ollama pull qwen2.5:14b # ~9 GB, one-time download
# 2. Install BugHunter
git clone https://github.com/shuvonsec/claude-bug-bounty.git
cd claude-bug-bounty
./install.sh --agent standalone # creates system-wide 'bughunter' command
# 3. Hunt
bughunter setup # choose Ollama
bughunter recon target.com
export GROQ_API_KEY="your-key-here" # free at console.groq.com
./install.sh --agent standalone
bughunter setup # choose Groq
bughunter hunt target.com
选项 A — 独立模式(无需订阅,人人可用)
git clone https://github.com/shuvonsec/claude-bug-bounty.git
cd claude-bug-bounty
./install.sh --agent standalone # creates system-wide 'bughunter' command
bughunter setup # pick a free AI provider
bughunter recon target.com
bughunter hunt target.com
bughunter validate "my finding"
bughunter report
选项 B — Claude Code 插件 (需要 Claude Code)
git clone https://github.com/shuvonsec/claude-bug-bounty.git
cd claude-bug-bounty
chmod +x install_tools.sh && ./install_tools.sh # subfinder · httpx · nuclei · katana · ffuf
chmod +x install.sh && ./install.sh # skills + commands → ~/.claude/
claude
/recon target.com # map the attack surface
/hunt target.com # test for vulnerabilities
/validate # run the 7-Question Gate
/report # write the submission
选项 C — 让 Claude 安装它 (仅限 Claude Code)
打开终端,运行 claude,然后粘贴:
Install the Claude Bug Bounty toolkit from https://github.com/shuvonsec/claude-bug-bounty
into ~/tools/. Clone the repo, run ./install_tools.sh then ./install.sh.
Verify /recon /hunt /validate /report are available.
| Command | 功能 |
|---|---|
/web3-audit <contract.sol> | 10 类智能合约审计,附带 Foundry PoC 模板 |
/token-scan <contract> | Rug pull 扫描器 — 铸币权限 · LP 锁定 · 蜜罐 · 联合曲线 |
九个专家,各自专精一项工作:
You ─▶ /recon ─▶ /hunt ─▶ /validate ─▶ /report
│ │
▼ ▼
Hunt Memory 7-Question Gate
(persists across (kills weak findings
sessions) before you submit)
流水线中的每个工具都会根据是否安装进行门控——缺失的工具会被跳过,而不会报错。设置一次的 Auth 标头会自动贯穿 httpx · katana · ffuf · nuclei · dalfox。
claude-bug-bounty/
│
├── skills/ # AI knowledge bases — loaded as /skill-name
│ ├── bug-bounty/ # Master workflow — all vuln classes, LLM testing, chains
│ ├── bb-methodology/ # Hunting mindset · 5-phase workflow · session discipline
│ ├── web2-recon/ # Subdomain enum · live host discovery · URL crawl
│ ├── web2-vuln-classes/ # 21 bug classes with bypass tables
│ ├── security-arsenal/ # Payloads · bypass tables · gf patterns
│ ├── triage-validation/ # 7-Question Gate · 4 gates · never-submit list
│ ├── report-writing/ # Templates for H1 · Bugcrowd · Intigriti · Immunefi
│ ├── web3-audit/ # Smart contract bugs · Foundry PoC · 10 bug classes
│ ├── meme-coin-audit/ # Rug pull detection · LP attacks · bonding curve
│ └── credential-attack/ # Password spray methodology · legal guardrails
│
├── commands/ # 26 slash commands (/recon /hunt /validate /report …)
├── agents/ # 9 specialized AI agents (recon, validator, reporter …)
│
├── tools/ # Python + shell scanner pipeline (~35 tools)
│ ├── hunt.py # Master orchestrator
│ ├── recon_engine.sh # Subdomain + URL discovery
│ ├── vuln_scanner.sh # XSS · SQLi · SSRF · SSTI probe pipeline
│ ├── validate.py # 4-gate finding validator with identity checks
│ └── … # 30+ more scanners — see tools/README.md
│
├── memory/ # Cross-session hunt memory (pattern DB · audit log)
├── rules/ # Always-active hunting + reporting rules
├── tests/ # Regression test suite (pytest)
├── web3/ # 13-chapter smart contract audit guide
├── mcp/ # MCP integrations — Burp Suite · Caido · HackerOne API
├── wordlists/ # Curated wordlists + SecLists / PayloadsAllTheThings refs
├── scripts/ # Dork runner · full hunt pipeline
├── hooks/ # Claude Code hook configuration
├── site/ # bughunter.fun landing page
├── demo/ # Local vulnerable target for tutorial recordings
│
├── docs/ # Extended documentation
│ ├── advanced-techniques.md # Exploitation techniques + chaining strategies
│ ├── auth-sessions.md # Auth header management guide
│ ├── payloads.md # Payload reference for common vuln classes
│ ├── smart-contract-audit.md# Smart contract audit deep-dive
│ ├── TUTORIAL.md # A→Z video tutorial walkthrough
│ └── TODOS.md # Open improvement items
│
├── .github/ # GitHub community health files
│ ├── CONTRIBUTING.md # How to contribute
│ ├── CODE_OF_CONDUCT.md # Community standards
│ ├── SECURITY.md # Vulnerability reporting policy
│ ├── PULL_REQUEST_TEMPLATE.md
│ └── ISSUE_TEMPLATE/ # Bug report · Feature request · False positive
│
├── engine.py # Standalone CLI — 'bughunter' command, no subscription needed
├── brain.py # Multi-provider LLM layer (Ollama · Groq · DeepSeek · Claude · OpenAI)
├── agent.py # LangGraph-style ReAct hunting agent
├── install.sh # Install skills + commands → ~/.claude/ (or standalone mode)
├── install_tools.sh # Install subfinder · httpx · nuclei · katana · ffuf …
├── uninstall.sh # Remove skills + commands from ~/.claude/
├── uninstall_tools.sh # Remove external scanning tools
├── serve.py # Launch local demo target (python3 serve.py)
├── config.example.json # Auth session config template
├── requirements.txt # Python dependencies
├── CLAUDE.md # Claude Code plugin manifest (auto-loaded)
├── AGENTS.md # Multi-harness plugin guide (OpenCode · Codex · Pi)
├── SKILL.md # Master skill shortcut (auto-loaded by agent harnesses)
├── OPENCODE.md # OpenCode-specific installation guide
├── CHANGELOG.md # Version history
├── FAQ.md # Frequently asked questions
└── TERMS.md # Terms of use + authorized testing only
前提条件:
# macOS
brew install go python3 jq
# Linux (Ubuntu/Debian)
sudo apt install golang python3 jq
扫描工具(安装 subfinder · httpx · nuclei · katana · ffuf · gau · dnsx · nmap · dalfox 等):
chmod +x install_tools.sh && ./install_tools.sh
独立的 bughunter 命令(无需订阅,无需 Claude Code 即可使用):
./install.sh --agent standalone
bughunter setup # choose Ollama (free) · Groq (free tier) · DeepSeek (cheap) · Claude · OpenAI
将 AI 技能 + 命令安装到 Claude Code:
chmod +x install.sh && ./install.sh
其他智能体框架:
./install.sh --agent opencode # OpenCode
./install.sh --agent pi # Pi Agent
./install.sh --agent codex # Codex
./install.sh --agent all # every supported target
可选:Chaos API 密钥(更好的子域名覆盖)
export CHAOS_API_KEY="your-key"
echo 'export CHAOS_API_KEY="your-key"' >> ~/.zshrc
七条规则在每次会话中生效,没有例外:
欢迎提交 PR。以下最有价值:
skills/security-arsenal/SKILL.md 添加 Payloadgit checkout -b feature/your-contribution
git commit -m "feat: short description"
git push origin feature/your-contribution
| 提供商 | 费用 | 隐私 | 速度 | 开始使用 |
|---|
| Ollama | 100% 免费 · 本地运行 | 完全隐私 — 数据留在你的机器上 | 快 | ollama pull qwen2.5:14b |
| Groq | 提供免费套餐 | 云端 | 非常快 | console.groq.com → 获取 API 密钥 |
| DeepSeek | 非常便宜($0.001/1K tokens) | 云端 | 快 | platform.deepseek.com |
| Claude API | 付费 | 云端 | 快 | console.anthropic.com |
| OpenAI | 付费 | 云端 | 快 | platform.openai.com |
| OpenRouter | 订阅 / 按量付费 | 云端 | 快 | openrouter.ai/keys → 获取 API 密钥 |
| Command | 功能 |
|---|
/recon target.com | 子域名枚举 · 存活主机探测 · URL 爬取 · nuclei 扫描 |
/hunt target.com | 测试 IDOR · 认证绕过 · SSRF · XSS · SQLi · 逻辑缺陷等 |
/validate | 7-Question Gate — 在你浪费时间报告之前淘汰薄弱发现 |
/report | 60 秒内生成 H1 · Bugcrowd · Intigriti · Immunefi 提交报告 |
/autopilot target.com | 全自动完整流程 — 范围 → 侦察 → 狩猎 → 验证 → 报告 |
| Command | 功能 |
|---|
/surface target.com | 根据侦察数据 + 记忆对攻击面进行排序 |
/scope-aggregate <program> | 跨 H1 · Bugcrowd · Intigriti · YWH · Immunefi 的所有范围内资产 |
/cloud-recon --keyword <name> | 公开的 S3 · Azure · GCP 存储桶 + 绕过 CloudFlare 的源站 IP |
/param-discover <url> | 通过 Arjun · x8 发现隐藏的 HTTP 参数 |
/secrets-hunt --js-bundle <dir> | 在源代码、JS 包或 GitHub 组织中泄露的凭据 |
/takeover --recon <dir> | 通过 dnsReaper · subjack 发现子域名接管候选 |
/scan-cves <host> | 专注的 nuclei 高危/严重扫描 + 可选的 log4j-scan |
/bypass-403 <url> | 针对 403/401 的头部 · 方法 · 编码绕过技巧 |
| Command | 功能 |
|---|
/pickup target.com | 从上次会话恢复 — 优先处理未测试的端点 |
/intel target.com | 与该目标相关的 CVE + 已披露报告 |
/chain | 发现漏洞 A → 找出可与其链式利用的漏洞 B 和 C |
/scope <asset> | 在测试之前检查域名或 URL 是否在范围内 |
/triage | 快速 2 分钟 可行/不可行 检查 |
/remember | 将当前发现或技术记录到狩猎记忆 |
/memory-gc | 检查或轮转 hunt-memory JSONL 文件(上限 10 MB,3 个备份) |
/arsenal [tool] | 列出已安装的外部工具或打印安装提示 |
| 漏洞类型 | 典型赏金 |
|---|
| IDOR / BOLA | $500 – $5K |
| 认证绕过 | $1K – $10K |
| XSS(存储型 / 反射型 / DOM) | $500 – $5K |
| SSRF | $1K – $15K |
| 业务逻辑 | $500 – $10K |
| 竞争条件 | $500 – $5K |
| SQL 注入 | $1K – $15K |
| OAuth / OIDC | $500 – $5K |
| 文件上传 → RCE | $500 – $10K |
| GraphQL 认证绕过 | $1K – $10K |
| LLM / 提示注入 | $500 – $10K |
| API 错误配置(批量赋值 · JWT · CORS) | $500 – $5K |
| 账户接管 | $1K – $20K |
| SSTI | $2K – $10K |
| 子域名接管 | $200 – $5K |
| 云 / 基础设施暴露 | $500 – $20K |
| HTTP 请求走私 | $5K – $30K |
| 缓存投毒 | $1K – $10K |
| MFA / 2FA 绕过 | $1K – $10K |
| SAML / SSO 攻击 | $2K – $20K |
| 漏洞类型 | 典型赏金 |
|---|
| 账本失同步 | $50K – $2M |
| 访问控制 | $50K – $2M |
| 不完整的代码路径 | $50K – $2M |
| 差一错误 | $10K – $100K |
| 预言机操纵 | $100K – $2M |
| ERC4626 份额通胀 | $50K – $500K |
| 重入 | $10K – $500K |
| 闪电贷攻击 | $100K – $2M |
| 签名重放 | $10K – $200K |
| 代理 / 升级 | $50K – $2M |
| Agent | 角色 |
|---|
recon-agent | 子域名枚举 · 存活主机发现 · URL 爬取 |
report-writer | 影响力优先的报告,能获得赏金,而不是被标记为 N/A |
validator | 运行 7-Question Gate — 淘汰薄弱发现 |
web3-auditor | 覆盖 10 类漏洞的智能合约审计 |
chain-builder | 漏洞 A → 找出可与其链式利用的漏洞 B 和 C |
autopilot | 带安全检查点的完整狩猎循环 |
recon-ranker | 按最高价值目标优先对攻击面进行排序 |
token-auditor | Meme 币 / 代币 Rug pull 与安全扫描 |
credential-hunter | 字典生成 → OSINT → 泄露检查 → 喷洒(喷洒前硬性停止) |
| # | 规则 | 原因 |
|---|
| 1 | 先阅读完整范围 | 只测试项目授权的目标 |
| 2 | 只关注真实漏洞 | “攻击者现在就能利用这个吗?”——如果不能,停止 |
| 3 | 淘汰薄弱发现 | 30 秒的检查能节省数小时的无效报告时间 |
| 4 | 绝不超出范围 | 一个错误的请求就可能让你被封禁 |
| 5 | 5 分钟规则 | 5 分钟没有进展?换下一个 |
| 6 | 先验证再报告 | 在花 30 分钟撰写之前先运行 /validate |
| 7 | 影响力优先 | 优先测试后果最严重的漏洞 |