Agent skill · security · aradotso
metatron-pentest-assistant
AI-powered penetration testing assistant using local LLM (metatron-qwen via Ollama) on Parrot OS Linux
Why this skill is useful
Adds executable scripts for orchestrating penetration tests, integrating various recon tools, and managing a local AI model that aren't available in public documentation.
What it needs
Requires curl, dnsutils, mariadb, nikto, nmap, ollama, python3, whatweb, whois installed locally. About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
METATRON Penetration Testing Assistant Skill by ara.so — Daily 2026 Skills collection. METATRON is a CLI-based AI penetration testing assistant that runs entirely locally — no cloud, no API keys. It orchestrates recon tools (nmap, whois, whatweb, curl, dig, nikto), feeds results to a locally running fine-tuned LLM (metatron-qwen via Ollama), and stores all findings in MariaDB with full scan history, vulnerability tracking, and PDF/HTML export. --- Architecture Overview Database spine: every scan creates a slno in history; all other tables link via slno. --- Installation 1. Clone and set up Python environment 2. Install system recon tools 3. Install Ollama and pull base model 4. Build the custom metatron-qwen model Modelfile (the repo ships this — key parameters): To use 4b instead, edit Modelfile: Then rebuild: ollama create metatron-qwen -f Modelfile 5. Set up MariaDB Create all tables: Or manually (paste from README schema block). The 5 tables: history — one row per scan session (spine) vulnerabilities — findings per session fixes — remediation per vulnerability exploitsattempted — exploit attempts per session summary — raw scan + full AI analysis dump --- Running METATRON METATRON requires two terminals: Terminal 1 — Load model into memory: Terminal 2 — Launch the assistant: Main Menu Flow New Scan — Tool Selection Exporting Reports From View History → select scan → export: PDF — professional vulnerability report HTML — browser-viewable report --- Code Examples Programmatically run a scan and save to DB (db.py patterns) Running recon tools (tools.py patterns) Querying Ollama LLM (llm.py patterns) DuckDuckGo search and CVE lookup (search.py patterns) Full scan pipeline (end-to-end) --- Common Patterns Check if Ollama model is running before scan Query scan history Add a custom recon tool --- Troubleshooting metatron-qwen not found / connection refused Out of memory when running 9b model MariaDB connection error mysql.connector not found nmap requires root for SYN …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/metatron-pentest-assistant