BugHunter AI

Autonomous Bug Bounty Hunting Framework Powered by Claude Code + PAI

28 specialized AI agents. 8 orchestrated workflows. State-machine orchestration. 51 skills. Zero human input required.

Quick Start • Full Setup • Superpowers • Architecture • Agents • Prompts • Contributing

What is BugHunter AI?

BugHunter AI is an autonomous bug bounty hunting framework that turns Claude Code into an elite security researcher. Built on top of the PAI (Personal AI Infrastructure) system, it combines 20 specialized vulnerability agents, 51 skills, 13 expert AI agents, 20 lifecycle hooks, and a full offensive security toolchain into a single command:

# That's it. One command. Autonomous hunting.
hunt https://app.example.com

What happens next:

1. A state machine initializes and tracks 10 phases of the hunt
2. Credentials are loaded from an encrypted vault (never inline)
3. The app is profiled — flows mapped, tech stack fingerprinted, trust boundaries identified
4. Hypothesis-driven agents deploy in parallel — each with a specific attack theory
5. Findings are reported in real-time with CVSS scoring
6. A professional bug bounty report is generated automatically

Why BugHunter AI?

The Full Stack: PAI + Superpowers + BugHunter

BugHunter AI is not just a skill — it's part of a complete offensive security infrastructure. Here's what you get when you install the full setup:

PAI (Personal AI Infrastructure) v3.0

The foundation layer. PAI is a general problem-solving system that provides:

• The Algorithm (v1.5.0) — 7-phase structured reasoning (OBSERVE → THINK → PLAN → BUILD → EXECUTE → VERIFY → LEARN)
• 51 Skills — Specialized capabilities from security to content creation
• 13 Expert Agents — Architect, Engineer, Pentester, Researcher variants, QA Tester, and more
• 20 Lifecycle Hooks — Automated security validation, session management, algorithm tracking
• Cross-Session Memory — Persistent learning across conversations
• Voice System — ElevenLabs TTS integration with custom AI personality
• Multi-Channel Notifications — ntfy, Discord, Twilio alerts for long tasks and findings

Superpowers Plugin

Claude Code's official superpowers plugin adds enhanced capabilities:

• Extended tool access and MCP server integration
• Advanced agent orchestration with team mode
• Enhanced permission management

Security Skill Stack (16 Skills)

Expert Agent Army (13 Agents)

MCP Servers (3 Core + 5 Recommended)

Core (Pre-configured):

Recommended Security MCPs:

Plugins (4 Active)

Lifecycle Hooks (20 Hooks)

Architecture

flowchart TB
    subgraph Input["User Input"]
        A["hunt target.com"]
        B["hunt --config target.json"]
        C["hunt --apk app.apk"]
    end

    subgraph PAI["PAI Infrastructure (v3.0)"]
        direction TB
        ALG["The Algorithm (7 phases)"]
        SK["51 Skills"]
        HK["20 Hooks"]
        MEM["Cross-Session Memory"]
        VOICE["Voice System"]
    end

    subgraph Orchestrator["Hunt Orchestrator (State Machine)"]
        direction TB
        P0["Phase 0: INIT"]
        P1["Phase 1: MEMORY_LOAD"]
        P2["Phase 2: TARGET_INGEST"]
        P3["Phase 3: APP_UNDERSTANDING"]
        P4["Phase 4: RECON"]
        P5["Phase 5: AGENT_DEPLOY"]
        P6["Phase 6: DYNAMIC_TEST"]
        P7["Phase 7: VULN_ASSESS"]
        P8["Phase 8: LEARNING"]
        P9["Phase 9: REPORT"]

        P0 --> P1 --> P2 --> P3 --> P4 --> P5 --> P6 --> P7 --> P8 --> P9
    end

    subgraph Tools["Tool Layer"]
        V["Credential Vault"]
        AU["Auth Manager"]
        BB["Burp Bridge"]
        PW["Playwright Harness"]
        AP["Appium Harness"]
    end

    subgraph MCPs["MCP Servers"]
        BURP["Burp Suite MCP"]
        FS["Filesystem MCP"]
        GH["GitHub MCP"]
        SH["Shodan MCP"]
        VT["VirusTotal MCP"]
    end

    subgraph Agents["Agent Army (Parallel)"]
        direction LR
        AG1["XSSAgent"]
        AG2["SQLiAgent"]
        AG3["SSRFAgent"]
        AG4["IDORAgent"]
        AG5["AuthAgent"]
        AG6["LLMSecurityAgent"]
        AG7["APIAgent"]
        AG8["MobileAgent"]
        AG9["...12 more"]
    end

    subgraph SecuritySkills["Security Skills (16)"]
        direction LR
        SS1["WebAssessment"]
        SS2["SecurityHub"]
        SS3["APISecurityTesting"]
        SS4["PromptInjection"]
        SS5["...12 more"]
    end

    subgraph Output["Output"]
        R["Bug Bounty Report"]
        F["Real-time Findings"]
        D["Live Dashboard"]
        N["Notifications (ntfy/Discord/SMS)"]
    end

    Input --> PAI
    PAI --> Orchestrator
    P2 --> V
    P3 --> AU
    P3 --> BB
    P4 --> SecuritySkills
    P5 --> Agents
    P6 --> PW
    P6 --> AP
    Agents --> MCPs
    Agents --> F
    P9 --> R
    Orchestrator --> D
    F --> N

    style PAI fill:#1e3a5f,stroke:#3b82f6,color:#fff
    style Orchestrator fill:#1a1a2e,stroke:#e94560,color:#fff
    style Agents fill:#0f3460,stroke:#e94560,color:#fff
    style Tools fill:#16213e,stroke:#0f3460,color:#fff
    style MCPs fill:#1a1a3e,stroke:#00d2ff,color:#fff
    style SecuritySkills fill:#2d1b69,stroke:#8b5cf6,color:#fff
    style Input fill:#533483,stroke:#e94560,color:#fff
    style Output fill:#0f3460,stroke:#00d2ff,color:#fff

Quick Start

For the minimal BugHunter-only install:

git clone https://github.com/h4ckologic/bughunter-ai.git
cd bughunter-ai
./install.sh

For the full setup with PAI, Superpowers, and all security skills, see the Full Setup Guide.

Full Setup Guide

See SETUP.md for the complete, step-by-step guide to replicate the full infrastructure:

1. Install prerequisites (Claude Code, Bun, Go tools, Burp Suite)
2. Install PAI v3.0 (the foundation)
3. Configure your identity (DA + Principal)
4. Install plugins (Superpowers, claude-mem, ui-ux-pro-max)
5. Configure MCP servers (Burp, Filesystem, GitHub)
6. Install BugHunter AI skill
7. Set up optional security MCPs (Shodan, VirusTotal, NVD)
8. Configure notifications (ntfy, Discord, Twilio)
9. Verify the installation

Hunt Modes

hunt https://target.com                       # bounty mode (default)
hunt https://target.com --mode pentest        # pentest mode
hunt https://target.com --mode comprehensive  # comprehensive mode

Agents

BugHunter deploys 20 specialized agents, each an expert in one vulnerability class:

How Agents Work

Agents don't blindly scan. They receive specific hypotheses from the AppProfile:

Traditional scanning:          BugHunter AI:
"Run sqlmap on all URLs"   →   "The /api/v1/reports?filter= parameter
                                is passed into a PostgreSQL ORDER BY
                                clause — test time-based blind SQLi HERE"

This means 90% less noise and 10x faster confirmation.

Orchestrator Workflows

The hunt orchestrator classifies your target and dispatches the appropriate workflow. Each workflow defines its own phases, agent dispatch order, parallelism, and gate conditions.

How Workflows Work

hunt https://target.com
  │
  ├── Orchestrator classifies target type
  ├── Loads W_HUNT_WEB workflow
  ├── Phase 1: RECON (ReconAgent + SubdomainTakeoverAgent)
  ├── Phase 2: APP PROFILING (AppReviewAgent via dev-browser)
  ├── Phase 3: AUTH TESTING (AuthAgent)
  ├── Phase 4: INJECTION (SQLi + XSS + XXE + RCE — PARALLEL)
  ├── Phase 5: ACCESS CONTROL (IDOR + CORS + CSRF — PARALLEL)
  ├── Phase 6: BUSINESS LOGIC (BusinessLogic + RaceCondition — PARALLEL)
  ├── Phase 7: ADVANCED (SSRF + CachePoisoning + HTTPSmuggling + PrototypePollution — PARALLEL)
  ├── Phase 8: API/PROTOCOL (GraphQL + WebSocket + API — PARALLEL, conditional)
  ├── Phase 9: FILE HANDLING (FileUploadAgent, conditional)
  └── Phase 10: REPORTING (aggregate, score, deduplicate, generate report)

Each phase has gate conditions — the workflow only advances when the gate criteria are met. Agents within a phase run in parallel for maximum speed.

Tool Chain

Sample Prompts

Your First Hunt

hunt https://app.example.com

Hunt with Stored Credentials

Store credentials for example-corp: username [email protected], password SecureP@ss123

hunt https://app.example.com --creds vault:example-corp

Pentest Mode (Find More)

hunt https://staging.example.com --mode pentest

Hunt an AI Application

hunt https://ai-chatbot.example.com --mode pentest

Focus on AI-specific vulnerabilities:
- Extract the system prompt
- Test cross-user data access
- Try prompt injection (direct and indirect)
- Test RAG poisoning via document upload

Resume a Hunt

hunt https://app.example.com --resume

Full Power Hunt

hunt https://app.example.com using username [email protected] and password TestPass123

Use all available tools, skills, workflows, and MCPs.
Use Playwright and Burp MCPs to perform dynamic analysis.
Map the entire application attack surface.
Understand the application before attacking.
Find 10 high-severity vulnerabilities.
Don't stop until done.

Use Security Skills Directly

# Run a web assessment using the WebAssessment skill
/WebAssessment https://target.com

# Use the SecurityHub for guided methodology
/SecurityHub start assessment on https://target.com

# Run OSINT reconnaissance
/Recon https://target.com --deep

# Test LLM/AI security
/PromptInjection https://ai-app.com

See examples/sample-prompts.md for more.

Live Dashboard

Check hunt progress anytime:

hunt https://target.com --status

======================================================================
  HUNT STATUS: https://app.example.com
  Mode: BOUNTY | Elapsed: 45m | Findings: 3
  Min CVSS: 8.0 | Target: 10 findings
======================================================================
  [OK] INIT                  2s
  [OK] MEMORY_LOAD           1s
  [OK] TARGET_INGEST         3s
  [OK] APP_UNDERSTANDING     120s     (2 findings)
  [>>] RECON                 running...
  [  ] AGENT_DEPLOY
  [  ] DYNAMIC_TEST
  [  ] VULN_ASSESS
  [  ] LEARNING
  [  ] REPORT

  FINDINGS:
    F-001 [critical] SSRF: Webhook URL fetches AWS metadata
    F-002 [high] IDOR: Access other users' expense reports
    F-003 [high] XSS: Stored XSS in admin notification panel
======================================================================

Directory Structure

# BugHunter AI Skill (installed to ~/.claude/skills/)
~/.claude/skills/BugBountyFramework/
├── SKILL.md                     # Main skill definition (v2.0)
├── Agents/                      # 20 specialized vulnerability agents
│   ├── AppReviewAgent.md
│   ├── LLMSecurityAgent.md
│   ├── XSSAgent.md
│   ├── SQLiAgent.md
│   ├── SSRFAgent.md
│   ├── IDORAgent.md
│   ├── AuthAgent.md
│   ├── APIAgent.md
│   ├── CORSAgent.md
│   ├── FileUploadAgent.md
│   ├── XXEAgent.md
│   ├── RCEAgent.md
│   ├── BusinessLogicAgent.md
│   ├── MobileAgent.md
│   ├── WindowsAgent.md
│   ├── ReconAgent.md
│   ├── ReverseEngineeringAgent.md
│   ├── ExploitDevAgent.md
│   ├── DesktopAppAgent.md
│   └── LLMAgent.md
├── Tools/                       # TypeScript tools (Bun runtime)
│   ├── hunt-orchestrator.ts
│   ├── credential-vault.ts
│   ├── auth-manager.ts
│   ├── burp-bridge.ts
│   ├── playwright-harness.ts
│   └── appium-harness.ts
├── Templates/
│   ├── BugReport.md
│   └── TargetConfig.md
└── Wordlists/

# PAI Infrastructure (the foundation)
~/.claude/
├── settings.json                # Central config (identity, hooks, permissions, plugins)
├── CLAUDE.md                    # Entry point
├── .mcp.json                    # MCP server configuration
├── skills/                      # 51 skills
│   ├── PAI/                     # Core PAI system
│   ├── BugBountyFramework/      # This project
│   ├── WebAssessment/           # OWASP WSTG v5
│   ├── SecurityHub/             # Security command center
│   ├── OffensiveSecurityOrchestrator/
│   ├── APISecurityTesting/
│   ├── MobileSecurity/
│   ├── NetworkSecurity/
│   ├── CloudSecurity/
│   ├── ExploitDev/
│   ├── ReverseEngineering/
│   ├── MalwareAnalysis/
│   ├── PromptInjection/
│   ├── VulnResearch/
│   ├── SASTOrchestration/
│   ├── SCASecurity/
│   ├── ThreatModeling/
│   ├── Recon/
│   ├── RedTeam/
│   ├── OSINT/
│   ├── Research/                # Multi-engine research
│   ├── Browser/                 # Browser automation
│   ├── Fabric/                  # 240+ prompt patterns
│   └── ...35 more
├── agents/                      # 13 expert agent definitions
│   ├── Pentester.md
│   ├── Engineer.md
│   ├── Architect.md
│   └── ...10 more
├── hooks/                       # 20 lifecycle hooks
│   ├── SecurityValidator.hook.ts
│   ├── AlgorithmTracker.hook.ts
│   ├── LoadContext.hook.ts
│   ├── handlers/                # 7 hook handlers
│   └── lib/                     # 12 shared libraries
├── mcps/                        # Custom MCP servers
│   └── burp-mcp/
├── VoiceServer/                 # ElevenLabs TTS integration
└── MEMORY/                      # Persistent memory system
    ├── BugBounty/
    │   ├── Sessions/
    │   ├── Findings/
    │   ├── PatternDB/
    │   ├── LearningLogs/
    │   ├── TargetProfiles/
    │   └── Vault/
    ├── LEARNING/
    ├── SECURITY/
    ├── STATE/
    ├── WORK/
    └── VOICE/

How It Differs from Other Tools

Responsible Use

This framework is designed for authorized security testing only:

• Only test applications you have written permission to test
• Bug bounty programs with clearly defined scope
• Penetration tests with signed engagement letters
• Your own applications in staging/development environments

BugHunter AI enforces scope: The framework includes hard scope enforcement that blocks testing out-of-scope targets. Configure your scope before hunting.

The maintainers are not responsible for misuse. Always follow your program's rules of engagement.

Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.

Ideas for contributions:

• New specialized agents (e.g., GraphQLAgent, WebSocketAgent)
• Additional auth strategy templates
• Better wordlists
• Integration with more MCP servers
• New security skills
• Improved report templates
• Bug fixes and documentation

License

MIT License. See LICENSE for details.

Acknowledgements

• Anthropic — Claude Code, the AI engine behind everything
• Daniel Miessler / PAI — Personal AI Infrastructure v3.0 — the foundation layer providing the Algorithm (v1.5.0), 51 skills, 13 expert agents, 20 lifecycle hooks, cross-session memory, and the structured reasoning framework that makes autonomous hunting possible
• Claude Code Superpowers — Official Claude Code plugin enabling enhanced tool access, advanced agent orchestration with team mode, and extended MCP server integration that powers parallel agent deployment
• claude-mem — Persistent cross-session memory plugin that enables BugHunter's learning system to remember techniques, patterns, and findings across hunts
• PortSwigger — Burp Suite integration via custom MCP bridge
• ProjectDiscovery — Nuclei, httpx, subfinder, naabu — the recon backbone
• Playwright — Browser automation for dynamic testing and app profiling
• Bun — TypeScript runtime powering all tools and hooks
• ElevenLabs — Voice synthesis for the PAI notification and voice system
• ntfy — Push notifications for long-running hunts

Built with Claude Code + PAI by h4ckologic

If BugHunter AI helps you find bugs, give it a star!