Security
HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
arXiv cs.CR0 views
arXiv:2510.12200v2 Announce Type: replace Abstract: Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, modern web applications demand visual understanding, dynamic content handling, and multi-step interactions that only computer-use agents (CUAs) can perform. Yet, their ability to discover and exploit vulnerabilities through graphical interfaces remains largely unexplored. We present HackWorld, the first framework for systematically evaluating CUAs' capabilities to exploit web application vulnerabilities via visual interaction. Unlike sanitized benchmarks, HackWorld includes 36 real-world applications across 11 frameworks and 7 languages, featuring realistic flaws such as injection vulnerabilities, authentication bypasses, and unsafe input handling. Using a Capture-the-Flag (CTF) setup, it tests CUAs' capacity to identify and exploit these weaknesses while navigating complex web interfaces. Evaluation of state-of-the-art CUAs reveals concerning trends: exploitation rates below 12% and low cybersecurity awareness. CUAs often fail at multi-step attack planning and misuse security tools. These results expose the current limitations of CUAs in web security contexts and highlight opportunities for developing more security-aware agents capable of effective vulnerability detection and exploitation.
Source:https://arxiv.org/abs/2510.12200PreviousCyber-Zero: Training Cybersecurity Agents without RuntimeNextFrom TS-SUF-2 to TS-SUF-4: Practical Security Enhancements for FROST2 Threshold Signatures
Related posts
From TS-SUF-2 to TS-SUF-4: Practical Security Enhancements for FROST2 Threshold Signatures
0arXiv cs.CR
The Secret-Broker Pattern: Stop Handing Credentials to Your AI Agent
0dev.to Security
Actively exploited this week: 12 new CISA KEV entries (9 November to 15 November 2026)
0dev.to DevOps
The Future of Cybersecurity: Is It Worth Learning in 2027?
0dev.to Career
Agent Security Meets Regulatory Reality -- A Practitioner Systematization of Autonomous-Agent Threats and Controls in Regulated Financial Systems
0arXiv cs.SE
iGRAIL: Blockchain-Based Generative Federated Learning for Trustworthy Healthcare Intelligence
0arXiv cs.CR