AgentGuard: A Multi-Agent Framework for Robust Package Confusion Detection via Hybrid Search and Metadata-Content Fusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yu, Ma, Wei, Chen, Zhi, Liu, Ye, Jiang, Lingxiao, Tao, Junyi, Liu, Hao, Lyu, Yongqiang, Hu, Qiang
Format:	Preprint
Published:	2026
Subjects:	Software Engineering Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ConfuGuard: Using Metadata to Detect Active and Stealthy Package Confusion Attacks Accurately and at Scale
by: Jiang, Wenxin, et al.
Published: (2025)

AgentGuard: An Attribute-Based Access Control Framework for Tool-Use LLM-Based Agent
by: Luo, Jiaqi, et al.
Published: (2026)

AgentGuard: Repurposing Agentic Orchestrator for Safety Evaluation of Tool Orchestration
by: Chen, Jizhou, et al.
Published: (2025)

MARD: A Multi-Agent Framework for Robust Android Malware Detection
by: Zeng, Xueying, et al.
Published: (2026)

FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing
by: Lyu, Yunlong, et al.
Published: (2026)

CHASE: LLM Agents for Dissecting Malicious PyPI Packages
by: Toda, Takaaki, et al.
Published: (2026)

LLMs as Firmware Experts: A Runtime-Grown Tree-of-Agents Framework
by: Zhang, Xiangrui, et al.
Published: (2025)

An Analysis of Malicious Packages in Open-Source Software in the Wild
by: Zhou, Xiaoyan, et al.
Published: (2024)

Vital: Vulnerability-Oriented Symbolic Execution via Type-Unsafe Pointer-Guided Monte Carlo Tree Search
by: Tu, Haoxin, et al.
Published: (2024)

Bridging Expert Reasoning and LLM Detection: A Knowledge-Driven Framework for Malicious Packages
by: Guo, Wenbo, et al.
Published: (2026)

VulnRepairEval: An Exploit-Based Evaluation Framework for Assessing Large Language Model Vulnerability Repair Capabilities
by: Wang, Weizhe, et al.
Published: (2025)

Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities
by: Ma, Yujie, et al.
Published: (2026)

Cutting the Gordian Knot: Detecting Malicious PyPI Packages via a Knowledge-Mining Framework
by: Guo, Wenbo, et al.
Published: (2026)

A Large-scale Fine-grained Analysis of Packages in Open-Source Software Ecosystems
by: Zhou, Xiaoyan, et al.
Published: (2024)

LLM Security Guard for Code
by: Kavian, Arya, et al.
Published: (2024)

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-based Agents in Security Patch Detection
by: Han, Junxiao, et al.
Published: (2025)

PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
by: Liu, Xiting, et al.
Published: (2026)

LLM-Powered Detection of Price Manipulation in DeFi
by: Liu, Lu, et al.
Published: (2025)

An Empirical Study of Vulnerable Package Dependencies in LLM Repositories
by: Liu, Shuhan, et al.
Published: (2025)

Conflicting Scores, Confusing Signals: An Empirical Study of Vulnerability Scoring Systems
by: Koscinski, Viktoria, et al.
Published: (2025)

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
by: Liu, Bin, et al.
Published: (2025)

Exploiting LLM Agent Supply Chains via Payload-less Skills
by: Liu, Xinyu, et al.
Published: (2026)

AgentGuard: Runtime Verification of AI Agents
by: Koohestani, Roham
Published: (2025)

MindGuard: Intrinsic Decision Inspection for Securing LLM Agents Against Metadata Poisoning
by: Wang, Zhiqiang, et al.
Published: (2025)

LeakGuard: Detecting Memory Leaks Accurately and Scalably
by: Liang, Hongliang, et al.
Published: (2025)

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
by: Weng, Shihao, et al.
Published: (2026)

Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning
by: Ni, Ronghao, et al.
Published: (2026)

HarnessAgent: Scaling Automatic Fuzzing Harness Construction with Tool-Augmented LLM Pipelines
by: Yang, Kang, et al.
Published: (2025)

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair
by: Gajjar, Jugal, et al.
Published: (2025)

Automatically Generating Rules of Malicious Software Packages via Large Language Model
by: Zhang, XiangRui, et al.
Published: (2025)

An Empirically Grounded Reference Architecture for Software Supply Chain Metadata Management
by: Tran, Nguyen Khoi, et al.
Published: (2023)

SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
by: Guo, Zihan, et al.
Published: (2026)

What Makes a Good LLM Agent for Real-world Penetration Testing?
by: Deng, Gelei, et al.
Published: (2026)

False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models
by: Jiang, Weipeng, et al.
Published: (2026)

DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
by: Huang, Li, et al.
Published: (2026)

HighGuard: Cross-Chain Business Logic Monitoring of Smart Contracts
by: Eshghie, Mojtaba, et al.
Published: (2023)

Beyond Metadata: Code-centric and Usage-based Analysis of Known Vulnerabilities in Open-source Software
by: Ponta, Serena E., et al.
Published: (2018)

What You Trust Is Insecure: Demystifying How Developers (Mis)Use Trusted Execution Environments in Practice
by: Niu, Yuqing, et al.
Published: (2025)

Securing the Software Package Supply Chain for Critical Systems
by: Murali, Ritwik, et al.
Published: (2025)

A Static Analysis of Popular C Packages in Linux
by: Ruohonen, Jukka, et al.
Published: (2024)