8000
Skip to content

shuvonsec/claude-bug-bounty

Repository files navigation

Claude Bug Bounty Logo

v4.1.0

Claude Bug Bounty

Find security vulnerabilities, get paid — with AI doing the heavy lifting

Your AI hunting partner that remembers past targets, spots vulnerabilities, and writes reports for you.
The community made a meme coin to support the project CA: J6VzBAGnyyNEyzyHhauwg3ofRctFxnTLzQCcjUdGpump by shuvonsec


License: MIT Python 3.8+ Tests Claude Code


What Is This?  |  Quick Start  |  Commands  |  What's New  |  Install  |  FAQ  |  Terms


  14 commands  ·  8 AI agents  ·  9 skill domains
  20 web2 vuln classes  ·  10 web3 bug classes
  Burp MCP  ·  HackerOne MCP  ·  Autonomous Mode



What Is This?

Bug bounty hunting is when companies pay you real money to find security vulnerabilities in their websites and apps before bad actors do. Platforms like HackerOne and Bugcrowd connect hunters with companies. Payouts range from $100 to $1,000,000+ depending on severity.

This tool is a plugin for Claude Code (Anthropic's AI coding assistant) that turns it into a professional bug bounty hunting partner. Instead of juggling 15 different tools and writing reports from scratch, you just type a command and the AI handles the rest.

In plain terms:

  • You give it a target website
  • It automatically scans the site, finds vulnerabilities, validates they're real, and writes a professional report
  • It remembers what you found on past targets and applies that knowledge to new ones
  • You can even put it on autopilot and let it hunt on its own while you sleep

Who is it for?

  • Security researchers who want to move faster
  • Bug bounty hunters who are tired of the manual grind
  • People learning security who want AI guidance at every step



The Problem (Before This Tool)

Most hunters waste hours on things that shouldn't take that long:

  • Manually running 10+ tools in the right order just to map a target
  • Writing the same report structure from scratch every single time (45 min each)
  • Forgetting that a technique worked on a similar target 3 months ago
  • Submitting bugs that get rejected because they weren't properly validated first
  • Jumping between terminal windows, browser, notes, and report drafts

The Solution (After This Tool)

Before After
Run 10+ tools manually, hope for the best AI orchestrates everything in the right order
Write reports from scratch (45 min each) Report-writer agent generates submission-ready reports in 60s
Forget what worked last month Memory system — patterns from target A inform target B
Submit bugs without proper validation 7-Question Gate kills weak findings before you waste time reporting
Can't see live browser traffic Burp MCP — AI reads your proxy history in real time
Hunt one endpoint at a time /autopilot runs the full hunt loop while you watch



Quick Start

Prerequisite: You need Claude Code installed. It's Anthropic's free AI coding tool that runs in your terminal.

Step 1 — Install tools + skills

git clone https://github.com/shuvonsec/claude-bug-bounty.git
cd claude-bug-bounty
chmod +x install_tools.sh && ./install_tools.sh   # installs scanning tools (subfinder, httpx, nuclei...)
chmod +x install.sh && ./install.sh               # installs AI skills + commands into Claude Code

Step 2 — Start hunting

claude                          # open Claude Code in your terminal

/recon target.com               # step 1: map the target (subdomains, live pages, URLs)
/hunt target.com                # step 2: test for vulnerabilities
/validate                       # step 3: make sure the finding is real before writing it up
/report                         # step 4: generate a professional submission report

That's the core loop. Four commands, full workflow.

Step 3 — Go autonomous

/autopilot target.com --normal  # AI does the whole thing, pauses for your review at the end
/pickup target.com              # continue where you left off on a previous target
/intel target.com               # get CVEs + disclosed reports relevant to this target

Don't use Claude Code? Run the Python tools directly:

python3 tools/hunt.py --target target.com
./tools/recon_engine.sh target.com



How It Works

Think of it like a team of specialists, each doing one job:

                        YOU
                         |
                   ┌─────▼─────┐
                   │   Claude   │ ◄── Burp MCP (sees your browser traffic)
                   │   Code     │ ◄── HackerOne MCP (program intel)
                   └─────┬─────┘
                         |
         ┌───────────────┼───────────────┐
         |               |               |
   ┌─────▼─────┐  ┌──────▼──────┐  ┌────▼────┐
   │   Recon    │  │    Hunt     │  │ Report  │
   │  (map it)  │  │  (test it)  │  │(write it│
   └─────┬─────┘  └──────┬──────┘  └────┬────┘
         |               |               |
   finds all         checks for      formats for
   subdomains,       vulnerabilities  HackerOne /
   URLs, APIs        & validates      Bugcrowd /
                     findings         Immunefi
         |               |               |
   ┌─────▼───────────────▼───────────────▼─────┐
   │              Hunt Memory                   │
   │   remembers everything across sessions     │
   └────────────────────────────────────────────┘

Each step feeds the next. Claude orchestrates all of it, or you run any step on its own.




Commands

The Core 4 (start here)

Command What It Does When To Use
/recon target.com Maps the target — finds all subdomains, live pages, APIs, and runs basic scans Always first
/hunt target.com Actively tests for vulnerabilities using the right technique for the tech stack After recon
/validate Runs a 7-question check to confirm a finding is real before you write it up Before every report
/report Generates a professional submission report for H1/Bugcrowd/Intigriti/Immunefi After validation

Power Commands

Command What It Does
/autopilot target.com AI runs the full loop automatically — recon → hunt → validate → report
/surface target.com Shows a ranked list of the best places to test (based on your past findings)
/pickup target.com Shows untested endpoints from last session and picks up where you left off
/remember Saves the current finding or technique to memory for future use
/intel target.com Pulls CVEs and past disclosed reports relevant to this target
/chain When you find bug A, this finds bugs B and C that usually come with it
/scope <asset> Checks if a domain or URL is in scope before you test it
/triage Quick 2-minute go/no-go check — should you keep investigating or move on?
/web3-audit <contract> Full smart contract security audit with 10 bug class checklist
/token-scan <contract> Scans a meme coin or token for rug pull signals (EVM + Solana)



AI Agents

8 specialized agents, each built for one job:

Agent What It Does
recon-agent Finds all subdomains, live hosts, and URLs for a target
report-writer Writes professional, impact-first reports that get paid
validator Runs the 7-Question Gate — kills weak findings before you waste time
web3-auditor Audits smart contracts for 10 common vulnerability classes
chain-builder When you find one bug, finds the chain of related bugs
autopilot Runs the whole hunt loop autonomously with safety checkpoints
recon-ranker Ranks the attack surface so you test the highest-value targets first
token-auditor Fast meme coin / token rug pull and security analysis



What's New

v4.1.0 — Auto-Memory + README (Apr 2026)

  • Auto-memory at session end — the AI now automatically logs what it tested and found after every hunt session. Memory used to stay empty until you manually ran /remember. Now the flywheel starts on day 1.
  • README badge and stats updated, install_tools.sh added to Quick Start (was missing)
  • hunt-memory/ added to .gitignore (contains full URL history, shouldn't be committed)

v4.0.0 — Meme Coin Security Module (Apr 2026)

  • /token-scan <contract> — automated rug pull scanner for EVM and Solana tokens
  • skills/meme-coin-audit/ — 8 token bug classes: mint authority, freeze authority, LP locks, honeypot detection, bonding curve exploits, Solana SPL checks
  • New agent: token-auditor

v3.1.1 — CI/CD Scanner (Mar 2026)

  • GitHub Actions security scanning built into the recon pipeline
  • Auto-detects GitHub orgs from recon data and scans their workflow files
  • 52 rules, 81.6% GHSA coverage — catches expression injection, secret leaks, supply chain attacks
Older releases (v3.1.0, v3.0.0, v2.x)

v3.1.0 — Hunting Methodology Skill

  • skills/bb-methodology/ — mindset + 5-phase non-linear workflow, decision trees per vuln class, 20-min rotation clock

v3.0.0 — The Bionic Hunter

  • /autopilot — full autonomous hunt loop with --paranoid, --normal, --yolo modes
  • Hunt memory — journal, pattern DB, target profiles, cross-target learning
  • Burp MCP — AI reads your proxy history in real time
  • HackerOne MCP — search disclosed reports, get program stats and policy
  • /intel, /pickup, /remember, /surface commands

v2.1.0 — 20 Vuln Classes

  • MFA/2FA bypass and SAML/SSO attacks added (classes 19 and 20)
  • NoSQL injection, command injection, SSTI, HTTP smuggling, WebSocket payloads added to arsenal



What It Can Find

20 Web2 Vulnerability Classes — click to expand

These are the types of security bugs it looks for in regular websites and APIs:

Vulnerability What It Means Typical Payout
IDOR Accessing another user's data by changing a number in the URL $500 - $5K
Auth Bypass Getting into accounts or admin panels without permission $1K - $10K
XSS Injecting malicious scripts into web pages $500 - $5K
SSRF Making the server fetch internal resources it shouldn't $1K - $15K
Business Logic Exploiting flaws in how the app is supposed to work $500 - $10K
Race Conditions Sending requests at the same time to get double rewards/credits $500 - $5K
SQL Injection Manipulating the database through user inputs $1K - $15K
OAuth/OIDC Breaking the "Login with Google/GitHub" flows $500 - $5K
File Upload Uploading malicious files that get executed $500 - $5K
GraphQL Auth bypass and data leaks through GraphQL APIs $1K - $10K
LLM/AI Prompt injection and IDOR in AI-powered features $500 - $10K
API Misconfig Mass assignment, JWT attacks, broken CORS $500 - $5K
Account Takeover Taking over someone else's account $1K - $20K
SSTI Template injection that leads to code execution $2K - $10K
Subdomain Takeover Claiming expired subdomains (GitHub Pages, S3, Heroku) $200 - $5K
Cloud/Infra Exposed S3 buckets, EC2 metadata, Firebase, Kubernetes $500 - $20K
HTTP Smuggling Confusing front-end and back-end servers to bypass security $5K - $30K
Cache Poisoning Poisoning CDN caches to serve malicious content to others $1K - $10K
MFA Bypass Getting past two-factor authentication $1K - $10K
SAML/SSO Breaking enterprise single sign-on implementations $2K - $20K
10 Web3 / Smart Contract Bug Classes — click to expand

These are bugs in blockchain smart contracts, common on Immunefi:

Vulnerability What It Means Typical Payout
Accounting Desync Contract's math gets out of sync with reality $50K - $2M
Access Control Functions that should be admin-only aren't $50K - $2M
Incomplete Code Path Edge cases that drain funds $50K - $2M
Off-By-One Math errors that let attackers take more than they should $10K - $100K
Oracle Manipulation Manipulating price feeds to exploit DeFi protocols $100K - $2M
ERC4626 Attacks Vault share inflation attacks $50K - $500K
Reentrancy Calling back into a contract before it finishes $10K - $500K
Flash Loan Using uncollateralized loans to manipulate prices $100K - $2M
Signature Replay Reusing signed transactions $10K - $200K
Proxy/Upgrade Exploiting upgradeable contract patterns $50K - $2M



Installation

What You Need First

# macOS
brew install go python3 node jq

# Linux (Ubuntu/Debian)
sudo apt install golang python3 nodejs jq

You also need Claude Code installed and a free account.

Install

git clone https://github.com/shuvonsec/claude-bug-bounty.git
cd claude-bug-bounty
chmod +x install_tools.sh && ./install_tools.sh   # scanning tools (subfinder, httpx, nuclei, etc.)
chmod +x install.sh && ./install.sh               # AI skills + commands into Claude Code

API Keys

Chaos API (recommended for better subdomain discovery)
  1. Sign up free at chaos.projectdiscovery.io
  2. Add your key:
export CHAOS_API_KEY="your-key-here"
echo 'export CHAOS_API_KEY="your-key-here"' >> ~/.zshrc
Optional keys (even better subdomain coverage)

Add to ~/.config/subfinder/config.yaml:




The Rules (Always Active)

These apply every session, no exceptions:

 1. READ FULL SCOPE FIRST   — only test what the program says you can
 2. ONLY REAL BUGS          — "Can an attacker do this RIGHT NOW?" if no, stop
 3. KILL WEAK FINDINGS FAST — 30-second check saves hours of wasted reporting
 4. NEVER GO OUT OF SCOPE   — one wrong request can get you banned
 5. 5-MINUTE RULE           — no progress after 5 min? move to the next target
 6. VALIDATE BEFORE REPORT  — run /validate before you spend 30 min writing
 7. IMPACT FIRST            — start with the bugs that have the worst consequences



Related Projects

Repo What It's For
claude-bug-bounty This — full hunting pipeline from recon to report
web3-bug-bounty-hunting-ai-skills Smart contract security — 10 bug classes, Foundry PoC templates
public-skills-builder Turns 500+ public bug writeups into Claude skill files



Contributing

PRs welcome. Best contributions:

  • New vulnerability scanners or detection modules
  • Payload additions to skills/security-arsenal/SKILL.md
  • Real-world methodology improvements (with evidence from paid reports)
  • Support for more platforms (YesWeHack, Synack, HackenProof)
git checkout -b feature/your-contribution
git commit -m "Add: short description"
git push origin feature/your-contribution



Connect

GitHub   |   Twitter   |   LinkedIn   |   Email



For authorized security testing only. Only test targets within an approved bug bounty program scope.
Never test systems without explicit written permission. Follow responsible disclosure.



MIT License · Built by bug hunters, for bug hunters.

If this helped you find a bug, leave a star ⭐

About

AI-powered bug bounty hunting from your terminal - recon, 20 vuln classes, autonomous hunting, and report generation. All inside Claude Code.

Topics

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors

0