mhtsec/ARTEX

What it solves

ARTEX is an autonomous penetration testing system designed to automate the complex process of security vulnerability discovery and exploitation. It replaces manual security probing with an AI-driven approach that can independently plan attack paths, execute tools, and track findings across a target's infrastructure.

How it works

The system employs a multi-agent architecture powered by the norma SDK, utilizing a "dual-graph" structure to manage information:

• Asset Graph: A global truth library that maps the relationships between domains, subdomains, services, and endpoints.
• Exploration Graph: A per-task record of the AI's reasoning process, linking goals, intents, facts, and findings into a "lineage chain."

An event-driven engine coordinates a Planner (which generates intents based on the current state of the graphs) and multiple Workers (which execute real-world tools like nmap or curl). To maintain stability in complex attack chains, the Planner uses a persistent todolist to ensure multi-step exploits are carried out in the correct sequence. Workers can also exchange information by searching through each other's execution traces to avoid redundant effort.

Who it’s for

Security researchers and developers interested in autonomous security testing, AI-driven vulnerability research, and the study of LLM-based agentic workflows for cybersecurity.

Highlights

• Autonomous Attack Chains: Capable of executing multi-step exploitation sequences via a shared, persistent planning list.
• Dual-Graph Architecture: Separates the "what is the target" (Asset Graph) from the "how it was tested" (Exploration Graph).
• Human-in-the-Loop: Includes a web interface for monitoring activity streams, approving tool calls, and interacting with the agent.
• Integrated Tooling: Features a built-in MITM proxy for traffic recording and seamless asset synchronization with ScopeSentry.
• Vulnerability Retesting: Dedicated agents to verify if previously discovered vulnerabilities have been fixed.