Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning

• URL: http://arxiv.org/abs/2604.20179v1
• Date: Wed, 22 Apr 2026 04:50:48 GMT
• Title: Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning
• Abstract summary: We implement a multi-stage agent pipeline to scan code, propose vulnerabilities, generate proof-of-concept exploits, and validate them.<n>For packages from public benchmarks, LLMVD$.$js confirms 84% of the vulnerabilities, compared to less than 22% for prior program analysis tools.
• Score: 7.678135270362941
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapidly evolving Node$.$js ecosystem currently includes millions of packages and is a critical part of modern software supply chains, making vulnerability detection of Node$.$js packages increasingly important. However, traditional program analysis struggles in this setting because of dynamic JavaScript features and the large number of package dependencies. Recent advances in large language models (LLMs) and the emerging paradigm of LLM-based agents offer an alternative to handcrafted program models. This raises the question of whether an LLM-centric, tool-augmented approach can effectively detect and confirm taint-style vulnerabilities (e.g., arbitrary command injection) in Node$.$js packages. We implement LLMVD$.$js, a multi-stage agent pipeline to scan code, propose vulnerabilities, generate proof-of-concept exploits, and validate them through lightweight execution oracles; and systematically evaluate its effectiveness in taint-style vulnerability detection and confirmation in Node$.$js packages without dedicated static/dynamic analysis engines for path derivation. For packages from public benchmarks, LLMVD$.$js confirms 84% of the vulnerabilities, compared to less than 22% for prior program analysis tools. It also outperforms a prior LLM-program-analysis hybrid approach while requiring neither vulnerability annotations nor prior vulnerability reports. When evaluated on a set of 260 recently released packages (without vulnerability groundtruth information), traditional tools produce validated exploits for few ($\leq 2$) packages, while LLMVD$.$js generates validated exploits for 36 packages.

Related papers

• Multi-Agent Taint Specification Extraction for Vulnerability Detection [49.27772068704498]
  Static Application Security Testing (SAST) tools using taint analysis are widely viewed as providing higher-quality vulnerability detection results.<n>We present SemTaint, a multi-agent system that strategically combines the semantic understanding of Large Language Models (LLMs) with traditional static program analysis.<n>We integrate SemTaint with CodeQL, a state-of-the-art SAST tool, and demonstrate its effectiveness by detecting 106 of 162 vulnerabilities previously undetectable by CodeQL.
  arXiv  Detail & Related papers  (2026-01-15T21:31:51Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• Learning to Triage Taint Flows Reported by Dynamic Program Analysis in Node.js Packages [10.447259698656884]
  Program analysis tools often produce large volumes of candidate vulnerability reports.<n>This paper investigates whether machine learning can be applied to prioritizing vulnerabilities reported by program analysis tools.
  arXiv  Detail & Related papers  (2025-10-23T16:58:02Z)
• Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models [75.29749026964154]
  Ourmethod reduces the average Attack Success Rate to 4.41% across multiple benchmarks.<n>Clean accuracy and utility are preserved within 0.5% of the original model.<n>The defense generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.
  arXiv  Detail & Related papers  (2025-10-11T15:47:35Z)
• JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering [73.962469626788]
  Jailbreak attacks against multimodal large language Models (MLLMs) are a significant research focus.<n>We propose JPS, underlineJailbreak MLLMs with collaborative visual underlinePerturbation and textual underlineSteering.
  arXiv  Detail & Related papers  (2025-08-07T07:14:01Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs [71.7892165868749]
  Commercial Large Language Model (LLM) APIs create a fundamental trust problem.<n>Users pay for specific models but have no guarantee that providers deliver them faithfully.<n>We formalize this model substitution problem and evaluate detection methods under realistic adversarial conditions.<n>We propose and evaluate the use of Trusted Execution Environments (TEEs) as one practical and robust solution.
  arXiv  Detail & Related papers  (2025-04-07T03:57:41Z)
• SCORE: Syntactic Code Representations for Static Script Malware Detection [9.502104012686491]
  Server-side script attacks can steal data, compromise credentials, and disrupt operations. We propose novel feature extraction and deep learning (DL)-based approaches for static script malware detection. Our approach achieves a true positive rate (TPR) up to 81% higher than leading signature-based antivirus solutions.
  arXiv  Detail & Related papers  (2024-11-12T20:58:04Z)
• Unveiling the Invisible: Detection and Evaluation of Prototype Pollution Gadgets with Dynamic Taint Analysis [4.8966278983718405]
  This paper proposes Dasty, the first semi-automated pipeline to help developers identify gadgets in their applications' software supply chain. Dasty targets server-side Node.js applications and relies on an enhancement of dynamic taint analysis. We use Dasty in a study of the most dependent-upon NPM packages to analyze the presence of gadgets leading to ACE.
  arXiv  Detail & Related papers  (2023-11-07T11:55:40Z)
• ZeroLeak: Using LLMs for Scalable and Cost Effective Side-Channel Patching [6.556868623811133]
  Security critical software, e.g., OpenSSL, comes with numerous side-channel leakages left unpatched due to a lack of resources or experts. We explore the use of Large Language Models (LLMs) in generating patches for vulnerable code with microarchitectural side-channel leakages.
  arXiv  Detail & Related papers  (2023-08-24T20:04:36Z)

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.