Lune

NDSS2025Top-tier venue

YuraScanner: Leveraging LLMs for Task-driven Web App Scanning

Aleksei Stafeev, Tim Recktenwald, Gianluca De Stefano, Soheil Khodayari, Giancarlo Pellegrino

Abstract

Web application scanners are popular and effective black-box testing tools, automating the detection of vulnerabilities by exploring and interacting with user interfaces. Despite their effectiveness, these scanners struggle with discovering deeper states in modern web applications due to their limited understanding of workflows. This study addresses this limitation by introducing YURASCANNER, a task-driven web application scanner that leverages large-language models (LLMs) to autonomously execute tasks and workflows. YURASCANNER operates as a goal-based agent, suggesting actions to achieve predefined objectives by processing webpages to extract semantic information. Unlike traditional methods that rely on user-provided traces, YURASCANNER uses LLMs to bridge the semantic gap, making it web application-agnostic. Using the XSS engine of Black Widow, YURASCANNER tests discovered input points for vulnerabilities, enhancing the scanning process's comprehensiveness and accuracy. We evaluated YURASCANNER on 20 diverse web applications, focusing on task extraction, execution accuracy, and vulnerability detection. The results demonstrate YURASCANNER's superiority in discovering new attack surfaces and deeper states, significantly improving vulnerability detection. Notably, YURASCANNER identified 12 unique zero-day XSS vulnerabilities, compared to three by Black Widow. This study highlights YURASCANNER's potential to revolutionize web application scanning with its automated, task-driven approach.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

8 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Generative Agents: Interactive Simulacra of Human Behavior cites Language Models are Few-Shot Learners
  • Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination cites PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing
  • Chasing Shadows: Pitfalls in LLM Security Research cites PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing
  • Chasing Shadows: Pitfalls in LLM Security Research cites Language Models are Few-Shot Learners
  • XSSky: Detecting XSS Vulnerabilities through Local Path-Persistent Fuzzing cites Black Widow: Blackbox Data-driven Web Scanning
  • State-Aware Fuzzing of JavaScript Engines with LLM-Guided Instrumentation cites PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers8

  1. Chasing Shadows: Pitfalls in LLM Security ResearchJonathan Evertz, Niklas Risse, Nicolai Neuer, Andreas Müller et al.NDSS 2026 · 17 citations
  2. Incident Response Planning Using a Lightweight Large Language Model with Reduced HallucinationKim Hammar, Tansu Alpcan, Emil C. LupuNDSS 2026 · 16 citations
  3. Permission Rationales in the Web Ecosystem: An Exploration of Rationale Text and Design PatternsYusra Elbitar, Soheil Khodayari, Marian Harbach, Gianluca De Stefano et al.CHI 2025 · 3 citations
  4. XSSky: Detecting XSS Vulnerabilities through Local Path-Persistent FuzzingYoukun Shi, Yuan Zhang, Tianhao Bai, Feng Xue et al.USENIX Security 2025
  5. State-Aware Fuzzing of JavaScript Engines with LLM-Guided InstrumentationWai Kin Wong, Dongwei Xiao, Anthony Cheuk Tung Lai, Ping Fan Ke et al.SOSP 2026

Builds on11

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
  3. PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration TestingGelei Deng, Yi Liu, Víctor Mayoral Vilches, Peng Liu et al.USENIX Security 2024 · 186 citations
  4. Automatic Web Testing Using Curiosity-Driven Reinforcement LearningYan Zheng, Yi Liu, Xiaofei Xie, Yepang Liu et al.ICSE 2021 · 75 citations
  5. Black Widow: Blackbox Data-driven Web ScanningBenjamin Eriksson, Giancarlo Pellegrino, Andrei SabelfeldS&P 2021 · 65 citations

Related papers

  1. Uncovering Hidden Attack Surfaces in Web Applications via Semantic-Aware Black-Box ScanningFukun Mei, Peiyang Li, Miao Chen, Beijie Hou et al.CCS 2026
  2. ReScan: A Middleware Framework for Realistic and Robust Black-box Web Application ScanningKostas Drakonakis, Sotiris Ioannidis, Jason PolakisNDSS 2023
  3. Enhancing Vulnerability Detection via Inter-procedural Semantic CompletionBozhi Wu, Chengjie Liu, Zhiming Li, Yushi Cao et al.ISSTA 2025 · 2 citations
  4. Toss a Fault to Your Witcher: Applying Grey-box Coverage-Guided Mutational Fuzzing to Detect SQL and Command Injection VulnerabilitiesErik Trickel, Fabio Pagani, Chang Zhu, Lukas Dresel et al.S&P 2023
  5. AutoScraper: A Progressive Understanding Web Agent for Web Scraper GenerationWenhao Huang, Zhouhong Gu, Chenghao Peng, Jiaqing Liang et al.EMNLP 2024 · 6 citations
Dusk over the sea between two cliffs drawn in fine vertical lines