Multi-Agent Penetration Testing AI for the Web

• URL: http://arxiv.org/abs/2508.20816v1
• Date: Thu, 28 Aug 2025 14:14:24 GMT
• Title: Multi-Agent Penetration Testing AI for the Web
• Authors: Isaac David, Arthur Gervais,
• Abstract summary: MAPTA is a multi-agent system for autonomous web application security assessment.<n>It combines large language model orchestration with tool-grounded execution and end-to-end exploit validation.<n>On the 104-challenge XBOW benchmark, MAPTA achieves 76.9% overall success.
• Score: 3.93181912653522
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• AWE: Adaptive Agents for Dynamic Web Penetration Testing [0.0]
  AWE is a memory-augmented multi-agent framework for autonomous web penetration testing.<n>It embeds structured, vulnerability-specific analysis pipelines within a lightweight LLM orchestration layer.<n>AWE achieves substantial gains on injection-class vulnerabilities.
  arXiv  Detail & Related papers  (2026-03-01T07:32:42Z)
• CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability [50.57373283154859]
  We present CVE-Factory, the first multiagent framework to achieve expert-level quality in automatically transforming vulnerability tasks.<n>It is also evaluated on the latest realistic vulnerabilities and achieves a 66.2% verified success.<n>We synthesize over 1,000 executable training environments, the first large-scale scaling of agentic tasks in code security.
  arXiv  Detail & Related papers  (2026-02-03T02:27:16Z)
• An Effective and Cost-Efficient Agentic Framework for Ethereum Smart Contract Auditing [8.735899453872966]
  Heimdallr is an automated auditing agent designed to overcome hurdles through four core innovations.<n>It minimizes context overhead while preserving essential business logic.<n>It then employs reasoning to detect complex vulnerabilities and automatically chain functional exploits.
  arXiv  Detail & Related papers  (2026-01-25T13:28:37Z)
• Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition [101.86739402748995]
  We run the largest public red-teaming competition to date, targeting 22 frontier AI agents across 44 realistic deployment scenarios.<n>We build the Agent Red Teaming benchmark and evaluate it across 19 state-of-the-art models.<n>Our findings highlight critical and persistent vulnerabilities in today's AI agents.
  arXiv  Detail & Related papers  (2025-07-28T05:13:04Z)
• WebGuard: Building a Generalizable Guardrail for Web Agents [59.31116061613742]
  WebGuard is the first dataset designed to support the assessment of web agent action risks.<n>It contains 4,939 human-annotated actions from 193 websites across 22 diverse domains.
  arXiv  Detail & Related papers  (2025-07-18T18:06:27Z)
• OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety [58.201189860217724]
  We introduce OpenAgentSafety, a comprehensive framework for evaluating agent behavior across eight critical risk categories.<n>Unlike prior work, our framework evaluates agents that interact with real tools, including web browsers, code execution environments, file systems, bash shells, and messaging platforms.<n>It combines rule-based analysis with LLM-as-judge assessments to detect both overt and subtle unsafe behaviors.
  arXiv  Detail & Related papers  (2025-07-08T16:18:54Z)
• PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages [16.130469984234956]
  PoCGen is a novel approach to autonomously generate and validate PoC exploits for vulnerabilities in npm packages.<n>This is the first fully autonomous approach to use large language models (LLMs) in tandem with static and dynamic analysis techniques for PoC exploit generation.
  arXiv  Detail & Related papers  (2025-06-05T12:37:33Z)
• CyberGym: Evaluating AI Agents' Cybersecurity Capabilities with Real-World Vulnerabilities at Scale [46.76144797837242]
  Large language model (LLM) agents are becoming increasingly skilled at handling cybersecurity tasks autonomously.<n>Existing benchmarks fall short, often failing to capture real-world scenarios or being limited in scope.<n>We introduce CyberGym, a large-scale and high-quality cybersecurity evaluation framework featuring 1,507 real-world vulnerabilities.
  arXiv  Detail & Related papers  (2025-06-03T07:35:14Z)
• BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems [62.17474934536671]
  We introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems.<n>To capture the vulnerability lifecycle, we define three task types: Detect (detecting a new vulnerability), Exploit (exploiting a specific vulnerability), and Patch (patching a specific vulnerability)<n>We evaluate 8 agents: Claude Code, OpenAI Codex CLI with o3-high and o4-mini, and custom agents with o3-high, GPT-4.1, Gemini 2.5 Pro Preview, Claude 3.7 Sonnet Thinking, and DeepSeek-R1.
  arXiv  Detail & Related papers  (2025-05-21T07:44:52Z)
• Does the Vulnerability Threaten Our Projects? Automated Vulnerable API Detection for Third-Party Libraries [11.012017507408078]
  We propose VAScanner, which can effectively identify vulnerable root methods causing vulnerabilities in TPLs. VAScanner eliminates 5.78% false positives and 2.16% false negatives owing to the proposed sifting and augmentation mechanisms. In a large-scale analysis of 3,147 projects using vulnerable TPLs, we find only 21.51% of projects were threatened by vulnerable APIs.
  arXiv  Detail & Related papers  (2024-09-04T14:31:16Z)
• Static Application Security Testing (SAST) Tools for Smart Contracts: How Far Are We? [14.974832502863526]
  In recent years, the importance of smart contract security has been heightened by the increasing number of attacks against them. To address this issue, a multitude of static application security testing (SAST) tools have been proposed for detecting vulnerabilities in smart contracts. In this paper, we propose an up-to-date and fine-grained taxonomy that includes 45 unique vulnerability types for smart contracts.
  arXiv  Detail & Related papers  (2024-04-28T13:40:18Z)
• LLMs in Web Development: Evaluating LLM-Generated PHP Code Unveiling Vulnerabilities and Limitations [0.0]
  This study evaluates the security of web application code generated by Large Language Models, analyzing 2,500 GPT-4 generated PHP websites. Our investigation focuses on identifying Insecure File Upload,sql Injection, Stored XSS, and Reflected XSS in GPT-4 generated PHP code. According to Burp's Scan, 11.56% of the sites can be straight out compromised. Adding static scan results, 26% had at least one vulnerability that can be exploited through web interaction.
  arXiv  Detail & Related papers  (2024-04-21T20:56:02Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.