Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PTHelper: An open source tool to support the Penetration Testing process

Jacobo Casado de Gracia, Alfonso Sánchez-Macián

TL;DR

PTHelper addresses the time-consuming and information-siloed nature of penetration testing by delivering a modular, open-source toolkit that automates the full pentest lifecycle while preserving human oversight. The system orchestrates four modules—Scanner, Exploiter, NLPAgent, and Reporter—to collect data, identify and prepare exploits, generate executive and finding reports via prompt-engineered NLP, and render a SAFR-formatted document. Demonstrations in black-box infrastructure and HackTheBox validate end-to-end functionality and real-world applicability, showing reduced tester interactions and a coherent integrated report workflow. The work contributes a practical, extensible framework that can evolve to cover web/mobile pentesting and performance optimizations, thereby accelerating secure-architecture assessments in enterprise settings.

Abstract

Offensive security is one of the state of the art measures to protect enterprises and organizations. Penetration testing, broadly called pentesting, is a branch of offensive security designed to find, rate and exploit these vulnerabilities, in order to assess the security posture of an organization. This process is often time-consuming and the quantity of information that pentesters need to manage might also be difficult to handle. This project takes a practical approach to solve the automation of pentesting and proposes a usable tool, called PTHelper. This open-source tool has been designed in a modular way to be easily upgradable by the pentesting community, and uses state of the art tools and artificial intelligence to achieve its objective.

PTHelper: An open source tool to support the Penetration Testing process

TL;DR

PTHelper addresses the time-consuming and information-siloed nature of penetration testing by delivering a modular, open-source toolkit that automates the full pentest lifecycle while preserving human oversight. The system orchestrates four modules—Scanner, Exploiter, NLPAgent, and Reporter—to collect data, identify and prepare exploits, generate executive and finding reports via prompt-engineered NLP, and render a SAFR-formatted document. Demonstrations in black-box infrastructure and HackTheBox validate end-to-end functionality and real-world applicability, showing reduced tester interactions and a coherent integrated report workflow. The work contributes a practical, extensible framework that can evolve to cover web/mobile pentesting and performance optimizations, thereby accelerating secure-architecture assessments in enterprise settings.

Abstract

Offensive security is one of the state of the art measures to protect enterprises and organizations. Penetration testing, broadly called pentesting, is a branch of offensive security designed to find, rate and exploit these vulnerabilities, in order to assess the security posture of an organization. This process is often time-consuming and the quantity of information that pentesters need to manage might also be difficult to handle. This project takes a practical approach to solve the automation of pentesting and proposes a usable tool, called PTHelper. This open-source tool has been designed in a modular way to be easily upgradable by the pentesting community, and uses state of the art tools and artificial intelligence to achieve its objective.
Paper Structure (19 sections, 8 figures, 1 table)

This paper contains 19 sections, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background
  3. Offensive Security and Penetration Testing
  4. Penetration testing lifecycle
  5. Pentest automation
  6. Architecture Overview
  7. A different approach to automation
  8. Scanner module
  9. Exploiter module
  10. NLPAgent module
  11. Applying prompt engineering to the agent
  12. Reporter module
  13. Implementation and results
  14. Tool usage and information
  15. Testing PThelper functionality
  16. ...and 4 more sections

Figures (8)

  • Figure 1: Graphical view of the penetration testing lifecycle.
  • Figure 2: Traditional pentesting methodology. Red lines indicate pentester interactions, black lines indicate the output of each process.
  • Figure 3: Pentesting methodology proposed by using PTHelper. Red lines indicate pentester interactions, purple lines indicate tool operations.
  • Figure 4: Scanner module operations and interactions
  • Figure 5: Exploiter module operations and interactions
  • ...and 3 more figures