# AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications

arXiv: https://arxiv.org/abs/2604.00704 · HTML: https://mlsanity.com/paper/2604.00704/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 17 of 17)

- [AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks](https://mlsanity.com/paper/2403.01038/) (2024)
- [Getting pwn'd by AI: Penetration Testing with Large Language Models](https://mlsanity.com/paper/2308.00121/) (2023)
- [The Art, Science, and Engineering of Fuzzing: A Survey](https://mlsanity.com/paper/1812.00140/) (2018)
- [PentestAgent: Incorporating LLM Agents to Automated Penetration Testing](https://mlsanity.com/paper/2411.05185/) (2024)
- [ChatGPT for Vulnerability Detection, Classification, and Repair: How Far Are We?](https://mlsanity.com/paper/2310.09810/) (2023)
- [A Survey of Symbolic Execution Techniques](https://mlsanity.com/paper/1610.00502/) (2016)
- [AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing](https://mlsanity.com/paper/2409.10737/) (2024)
- [VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2501.13411/) (2025)
- [PenHeal: A Two-Stage LLM Framework for Automated Pentesting and Optimal Remediation](https://mlsanity.com/paper/2407.17788/) (2024)
- [PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages](https://mlsanity.com/paper/2506.04962/) (2025)
- [PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level Design](https://mlsanity.com/paper/2512.14233/) (2025)
- [Automated Code-centric Software Vulnerability Assessment: How Far Are We? An Empirical Study in C/C++](https://mlsanity.com/paper/2407.17053/) (2024)
- [Good News for Script Kiddies? Evaluating Large Language Models for Automated Exploit Generation](https://mlsanity.com/paper/2505.01065/) (2025)
- [A Systematic Study on Generating Web Vulnerability Proof-of-Concepts Using Large Language Models](https://mlsanity.com/paper/2510.10148/) (2025)
- [Thou Shalt Not Depend on Me: Analysing the Use of Outdated JavaScript Libraries on the Web](https://mlsanity.com/paper/1811.00918/) (2018)
- [Countering the Path Explosion Problem in the Symbolic Execution of Hardware Designs](https://mlsanity.com/paper/2304.05445/) (2023)
- [Real-World Usability of Vulnerability Proof-of-Concepts: A Comprehensive Study](https://mlsanity.com/paper/2510.18448/) (2025)

## Abstract (arXiv)

Large-scale web applications are widely deployed with complex third-party components, inheriting security risks arising from component vulnerabilities. Security assessment is therefore required to determine whether such known vulnerabilities remain practically exploitable in real applications. Penetration testing is a widely adopted approach that validates exploitability by launching concrete attacks against known vulnerabilities in real-world black-box systems. However, existing approaches often fail to automatically generate reliable exploits, limiting their effectiveness in practical security assessment. This limitation mainly stems from two issues: (1) precisely triggering vulnerabilities with correct technical details, and (2) adapting exploits to diverse real-world deployment settings. In this paper, we propose AutoEG, a fully automated multi-agent framework for exploit generation targeting black-box web applications. AutoEG has two phases: First, AutoEG extracts precise vulnerability trigger logic from unstructured vulnerability information and encapsulates it into reusable trigger functions. Second, AutoEG uses trigger functions for concrete attack objectives and iteratively refines exploits through feedback-driven interaction with the target application. We evaluate AutoEG on 104 real-world vulnerabilities with 29 attack objectives, resulting in 660 exploitation tasks and 55,440 exploit attempts. AutoEG achieves an average success rate of 82.41%, substantially outperforming state-of-the-art baselines, whose best performance reaches only 32.88%.