WizCodes
WorkAbout
WizCodes

Production-ready web platforms, mobile apps, and AI systems. Based in Ahmedabad, India.

Serving clients in US · UK · Canada · Europe

hello@wizcodes.site
Ahmedabad, India · Est. 2025

Services

ServicesWeb DevelopmentMobile AppsAI AutomationIndustries we servePricing

Company

WorkAboutContact

Resources

BlogOpen SourceFAQTestimonials
Listed on
ClutchGoodFirmsThe Manifest
MSME CertifiedDUNS RegisteredGDPR & DPDP256-bit TLS100% code ownership
© 2026 WizCodes. All rights reserved.Ahmedabad, India — Global Clients
Privacy·Terms
  1. Home/
  2. Open Source/
  3. Cyber Bug Bounty Agent
CB

Cyber Bug Bounty Agent

Autonomous security-research pipeline: eight Claude agents across two LangGraph state graphs.

PythonMIT

What it does

A multi-agent system that runs the whole bug-bounty loop without a human in the middle. One graph handles intake — research the target, write the outreach, wait for permission. A second graph runs after approval: recon, scan, aggregate and validate the findings, generate the report, deliver it. A permission watcher polls for the reply that moves a target from the first graph to the second.

Architecture

Two LangGraph state graphs and a watcher, coordinated by a supervisor. Intake runs on the start command and stops atwaiting; the scan graph runs once permission comes back.

architecture
┌─────────────────────────────────────────────────────────────────────┐
│                        SUPERVISOR (Orchestrator)                     │
│           Builds & runs two LangGraph StateGraphs + watcher          │
├─────────────────────────────────────────────────────────────────────┤
│                                                                       │
│  INTAKE GRAPH (start command)         SCAN GRAPH (after approval)     │
│  ┌──────────────────────┐             ┌──────────────────────────┐   │
│  │ START                │             │ START                     │   │
│  │   ↓                  │             │   ↓                       │   │
│  │ ResearcherAgent      │             │ ReconAgent                │   │
│  │   ↓                  │             │   ↓                       │   │
│  │ OutreachAgent        │             │ ScannerAgent              │   │
│  │   ↓                  │             │   ↓                       │   │
│  │ END (status=waiting) │             │ AggregatorAgent (Opus)    │   │
│  └──────────────────────┘             │   ↓                       │   │
│                                       │ ReporterAgent             │   │
│  PERMISSION WATCHER (watch command)   │   ↓                       │   │
│  ┌──────────────────────┐             │ DeliveryAgent             │   │
│  │ Poll IMAP every N min│             │   ↓                       │   │
│  │   ↓                  │             │ END (status=delivered)    │   │
│  │ ClassifierAgent      │             └──────────────────────────┘   │
│  │   ↓                  │                                             │
│  │ Route: granted →     │                                             │
│  │   approve / auto-scan│                                             │
│  └──────────────────────┘                                             │
└─────────────────────────────────────────────────────────────────────┘

Agent roles

AgentModelPurpose
ResearcherAgentClaude SonnetOSINT gathering + company profiling
OutreachAgentClaude SonnetPersonalised email generation
ClassifierAgentClaude HaikuReply classification (granted / denied / ambiguous)
ReconAgentClaude SonnetAttack-surface analysis from recon tool output
ScannerAgent—Orchestrates the vulnerability scanning tools
AggregatorAgentClaude OpusDeduplicates, validates and CVSS-enriches all findings
ReporterAgent—Generates the PDF report via ReportLab
DeliveryAgentClaude SonnetWrites the delivery cover note

Core infrastructure

ModulePurpose
TokenAwareClientWraps every Anthropic API call with cost tracking, retry logic and network resilience
StageManagerRAM-aware sequential execution with GC, monitoring and emergency process kill
NetworkManagerDetects connectivity drops, waits for VPN restoration, retries operations
DatabaseManagerSQLite persistence — WAL mode, connection-per-call, parameterised queries
Notifierntfy.sh push notifications for every pipeline event
EmailSenderSMTP via Resend, which avoids Cloudflare blocking on VPN IPs
IMAPReceiverGmail IMAP polling for permission replies, via ImprovMX forwarding

Built with

  • Python
  • LangGraph
  • Claude API
  • Multi-agent
  • Security
  • SQLite

Get it

View on GitHub

The story behind it

This page covers how it is built. For what it does, why it exists and what it found, read the Cyber Agent case study.

Need something like this built for you?

We build production AI systems and developer tooling for clients, delivered end to end and handed over to your own accounts.

Get a free prototypeAI Automation →