ProfMalPlus: Agent-Coordinated Detection of Malicious NPM Packages via Static-Dynamic Analysis Synergy

• URL: http://arxiv.org/abs/2607.13965v1
• Date: Wed, 15 Jul 2026 15:52:11 GMT
• Title: ProfMalPlus: Agent-Coordinated Detection of Malicious NPM Packages via Static-Dynamic Analysis Synergy
• Abstract summary: ProfMalPlus is a malicious NPM package detector combining object-sensitive behavior graphs with coordinated LLM reasoning.<n>It identifies installation commands and entry files, then constructs graphs capturing sensitive APIs, third-party calls, and unresolved calls.<n>ProfMalPlus achieves a 98.1% F1-score, outperforming state-of-the-art detectors by 3.5% to 52.6%.
• Score: 23.914217277586477
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Open source software is vulnerable to supply-chain attacks through transitive dependencies, especially malicious code injected into NPM packages. Existing detectors often inadequately model obfuscated behavior, overlook JavaScript's object-centric features, poorly coordinate static and dynamic analysis, and lose semantic information during behavior abstraction. We propose ProfMalPlus, a malicious NPM package detector combining object-sensitive behavior graphs with coordinated LLM reasoning over annotated code slices. It identifies installation commands and entry files, then constructs graphs capturing sensitive APIs, third-party calls, and unresolved calls. From these graphs, ProfMalPlus extracts security-relevant slices and adds inline static analysis evidence. Local judge agents independently assess each slice. Self-consistency consolidates repeated judgements to reduce LLM variance, while a global judge synthesizes their reports into an entry-level verdict. For undetermined cases, a router selects either third-party enrichment, which adds registry derived module and method semantics, or dynamic augmentation, which executes the package in a sandbox to resolve runtime dependent behavior. The enriched evidence is fed back for reassessment. Finally, a localization agent reports malicious code snippets with explanations. ProfMalPlus achieves a 98.1% F1-score, outperforming state-of-the-art detectors by 3.5% to 52.6%. It also identified 597 previously unknown malicious packages, all confirmed and removed from NPM.

Related papers

• LMSM: LLM Security Framework Inspired by Linux Security Modules [56.93644694627783]
  Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them.<n>We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving.
  arXiv  Detail & Related papers  (2026-08-26T12:13:05Z)
• Fantastic Adaptive Taxonomies and How to Use Them [100.20614173157708]
  AdaMAST converts execution traces into a compact, evidence-grounded failure taxonomy.<n>No code is hand-authored, no trace human-annotated.<n>In agent-system search, taxonomy-coded diagnoses of failed candidates outperform free-form.
  arXiv  Detail & Related papers  (2026-07-17T17:41:16Z)
• AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration [6.39392731596656]
  Given a vulnerability-fixing commit, trigger localization asks which specific statement turns the vulnerable program state into a concrete unsafe operation.<n>We present AutoTrace, an agentic pipeline that localizes vulnerability triggers by exploring a code property graph layer by layer.<n>Agents never accept a trigger on their own authority; every reported trigger is backed by explicit evidence drawn from the graph.
  arXiv  Detail & Related papers  (2026-07-13T18:21:42Z)
• What to Test Next: Interpretable Coverage Gap Discovery in Driving VLMs [52.50210189669399]
  Driving vision-language models (VLMs) must accurately understand scenes across diverse conditions defined by Operational Design Domains (ODDs)<n>We propose SliceScorer, a deterministic scoring rule for missing-slice recommendation.<n>We show that SliceNav surfaces high-risk coverage gaps more effectively than prior slice-discovery methods.
  arXiv  Detail & Related papers  (2026-06-01T03:18:01Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection [32.301679396929536]
  We propose SysName, a framework that shifts the defensive paradigm from static input filtering to execution-aware analysis.<n>SysName synthesizes fragmented operational primitives into contiguous behavioral trajectories, enabling a holistic view of system activity.<n> Empirical evaluations demonstrate that SysName effectively detects over ten distinct compound attack vectors, achieving F1-scores of 85.3% and 66.7% for node-level and path-level end-to-end attack detection, respectively.
  arXiv  Detail & Related papers  (2026-03-04T01:59:16Z)
• Bridging Expert Reasoning and LLM Detection: A Knowledge-Driven Framework for Malicious Packages [10.858565849895314]
  Open-source ecosystems such as NPM and PyPI are increasingly targeted by supply chain attacks.<n>We present IntelGuard, a retrieval-augmented generation (RAG) based framework that integrates expert analytical reasoning into automated malicious package detection.
  arXiv  Detail & Related papers  (2026-01-23T05:31:12Z)
• 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)
• Towards Classifying Benign And Malicious Packages Using Machine Learning [2.8630136355252582]
  Malicious open-source package detection typically requires static, dynamic analysis, or both.<n>Current dynamic analysis tools lack an automatic method to differentiate malicious packages from benign packages.<n>We propose an approach to extract the features from dynamic analysis (e.g., executed commands) and leverage machine learning techniques to automatically classify packages as benign or malicious.
  arXiv  Detail & Related papers  (2025-11-19T01:59:11Z)
• Defending against Indirect Prompt Injection by Instruction Detection [109.30156975159561]
  InstructDetector is a novel detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.<n>InstructDetector achieves a detection accuracy of 99.60% in the in-domain setting and 96.90% in the out-of-domain setting, and reduces the attack success rate to just 0.03% on the BIPIA benchmark.
  arXiv  Detail & Related papers  (2025-05-08T13:04:45Z)
• DONAPI: Malicious NPM Packages Detector using Behavior Sequence Knowledge Mapping [28.852274185512236]
  npm is the most extensive package manager, hosting more than 2 million third-party open-source packages. In this paper, we synchronize a local package cache containing more than 3.4 million packages in near real-time to give us access to more package code details. We propose the DONAPI, an automatic malicious npm packages detector that combines static and dynamic analysis.
  arXiv  Detail & Related papers  (2024-03-13T08:38:21Z)

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.