---
title: "Multi-Agent Penetration Testing AI for the Web (arXiv:2508.20816) | Papers With Code Cyber"
description: "AI-powered development platforms are making software creation accessible to a broader audience, but this democratization has triggered a scalability crisis in security…"
canonical: "https://paperswithcode-cyber.com/paper/2508.20816"
type: "paper"
---

# Multi\-Agent Penetration Testing AI for the Web

arXiv:2508\.20816 · 2025-08-28

Authors: Isaac David, Arthur Gervais

## Abstract

AI\-powered development platforms are making software creation accessible to a broader audience, but this democratization has triggered a scalability crisis in security auditing\. With studies showing that up to 40% of AI\-generated code contains vulnerabilities, the pace of development now vastly outstrips the capacity for thorough security assessment\. We present MAPTA, a multi\-agent system for autonomous web application security assessment that combines large language model orchestration with tool\-grounded execution and end\-to\-end exploit validation\. On the 104\-challenge XBOW benchmark, MAPTA achieves 76\.9% overall success with perfect performance on SSRF and misconfiguration vulnerabilities, 83% success on broken authorization, and strong results on injection attacks including server\-side template injection \(85%\) and SQL injection \(83%\)\. Cross\-site scripting \(57%\) and blind SQL injection \(0%\) remain challenging\. Our comprehensive cost analysis across all challenges totals $21\.38 with a median cost of $0\.073 for successful attempts versus $0\.357 for failures\. Success correlates strongly with resource efficiency, enabling practical early\-stopping thresholds at approximately 40 tool calls or $0\.30 per challenge\. MAPTA's real\-world findings are impactful given both the popularity of the respective scanned GitHub repositories \(8K\-70K stars\) and MAPTA's low average operating cost of $3\.67 per open\-source assessment: MAPTA discovered critical vulnerabilities including RCEs, command injections, secret exposure, and arbitrary file write vulnerabilities\. Findings are responsibly disclosed, 10 findings are under CVE review\.

## Tasks

- [Exploit construction and validation](https://paperswithcode-cyber.com/tasks/cyberintel-exploit-development)
- [Penetration testing](https://paperswithcode-cyber.com/tasks/cyberintel-penetration-testing)

## Code repositories

- [arthurgervais/mapta](https://github.com/arthurgervais/mapta)

## Paper resources

- [Abstract page](https://arxiv.org/abs/2508.20816v1)
- [PDF](https://arxiv.org/pdf/2508.20816v1.pdf)