Skip to content

dasokkk/A6M5

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Version Python Platform AI

A6M5 — Recon & AI Analysis Tool

Recon automation tool that chains nmap, subfinder, nuclei, whatweb and other standard tools together, runs them concurrently, and feeds the output to a local LLM (Ollama) for vulnerability analysis.

⚠️ Disclaimer: Authorized security testing only. Get permission before scanning anything.


Features

  • Multi-tool recon pipeline (Whois, DNS, Subfinder, Nmap, WhatWeb, Nuclei)
  • Local AI analysis via Ollama — groups findings by severity, suggests exploits
  • 4 scan modes: fast, default, deep, custom
  • Built-in TCP alive check (no external httpx needed)

Dependencies

sudo apt install -y nmap whois dnsutils whatweb golang

Go tools

go install -v github.com/projectdiscovery/subfinder/v2/cmd/subfinder@latest
go install -v github.com/projectdiscovery/nuclei/v3/cmd/nuclei@latest
nuclei -update-templates

Ollama

curl -fsSL https://ollama.com/install.sh | sh
ollama pull llama3

Installation

git clone https://github.com/dasokkk/a6m5.git
cd a6m5

Usage

Interactive

python3 a6m5.py
a6m5 > example.com                  # Default mode
a6m5 > example.com -m fast          # Fast mode
a6m5 > example.com -m deep          # Deep mode  
a6m5 > example.com -m custom        # Custom wizard
a6m5 > help                         # Help menu
a6m5 > help modes                   # Show mode details

CLI

python3 a6m5.py -d example.com
python3 a6m5.py -d example.com -m fast
python3 a6m5.py -d example.com -m deep
python3 a6m5.py -d example.com -m custom

Scan Modes

Mode Nmap Nuclei Speed Use Case
fast Top 100 ports, no scripts Tech detection ~1-2 min CTF / quick check
default Top 1000, version + scripts CVEs + Misconfig ~5-10 min Standard pentest
deep All 65535 ports, aggressive Auto-scan ~30+ min Full audit
custom You configure You configure Varies Advanced

AI Analysis

The tool sends scan results to Ollama and generates ai_analysis.md grouped by severity:

# CRITICAL RISKS
1. CVE-2021-XXXXX — Apache RCE
   - Impact: Remote code execution
   - Exploit: msfconsole -x "use exploit/multi/http/apache_struts; set RHOSTS target; run"

# HIGH RISKS
1. Outdated OpenSSH 7.9
   - Impact: Auth bypass
   - Exploit: searchsploit openssh 7.9

To change the model, edit a6m5.py line ~484:

model = "llama3"  # swap to "mistral", "phi3", etc.

License

MIT


Built by dasok

About

Recon & AI Analysis Tool

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages