Copertina

From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Yiheng, Zhao, Zhijia, Chen, Bihuan, Wu, Susheng, Zhou, Zhuotong, Cao, Yiheng, Hu, Xin, Peng, Xin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Killing Two Birds with One Stone: Malicious Package Detection in NPM and PyPI using a Single Model of Malicious Behavior Sequence
di: Zhang, Junan, et al.
Pubblicazione: (2023)

Auditing MCP Servers for Over-Privileged Tool Capabilities
di: Huang, Charoes, et al.
Pubblicazione: (2026)

When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation
di: Zhao, Weibo, et al.
Pubblicazione: (2025)

VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection
di: Cao, Yiheng, et al.
Pubblicazione: (2026)

Detecting Malicious Intents in Smart Contracts with Pre-trained Programming Language Models
di: Huang, Youwei, et al.
Pubblicazione: (2025)

Lifting the Veil on Composition, Risks, and Mitigations of the Large Language Model Supply Chain
di: Huang, Kaifeng, et al.
Pubblicazione: (2024)

A Survey of Fuzzing Open-Source Operating Systems
di: Hu, Kun, et al.
Pubblicazione: (2025)

Malicious ML Model Detection by Learning Dynamic Behaviors
di: Nambiar, Sarang, et al.
Pubblicazione: (2026)

MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools
di: Tan, Zhuoran, et al.
Pubblicazione: (2026)

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

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

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

Similar but Patched Code Considered Harmful -- The Impact of Similar but Patched Code on Recurring Vulnerability Detection and How to Remove Them
di: Tan, Zixuan, et al.
Pubblicazione: (2024)

Mind the Gap: Evaluating LLMs for High-Level Malicious Package Detection vs. Fine-Grained Indicator Identification
di: Ryan, Ahmed, et al.
Pubblicazione: (2026)

DySec: A Machine Learning-based Dynamic Analysis for Detecting Malicious Packages in PyPI Ecosystem
di: Mehedi, Sk Tanzir, et al.
Pubblicazione: (2025)

"Elementary, My Dear Watson." Detecting Malicious Skills via Neuro-Symbolic Reasoning across Heterogeneous Artifacts
di: Wang, Shenao, et al.
Pubblicazione: (2026)

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

Fuzzing Frameworks for Server-side Web Applications: A Survey
di: Dharmaadi, I Putu Arya, et al.
Pubblicazione: (2024)

Poking Around in the Dark: Why a Shared Understanding of Components Matters
di: Reichmann, Felix, et al.
Pubblicazione: (2026)

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem
di: Song, Hao, et al.
Pubblicazione: (2025)

Triggering and Detecting Exploitable Library Vulnerability from the Client by Directed Greybox Fuzzing
di: Zhao, Yukai, et al.
Pubblicazione: (2026)

VulEval: Towards Repository-Level Evaluation of Software Vulnerability Detection
di: Wen, Xin-Cheng, et al.
Pubblicazione: (2024)

MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code
di: Ning, Kaiwen, et al.
Pubblicazione: (2024)

Unveiling A Hidden Risk: Exposing Educational but Malicious Repositories in GitHub
di: Masud, Md Rayhanul, et al.
Pubblicazione: (2024)

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

Are AI-assisted Development Tools Immune to Prompt Injection?
di: Huang, Charoes, et al.
Pubblicazione: (2026)

MalLoc: Toward Fine-grained Android Malicious Payload Localization via LLMs
di: Sun, Tiezhu, et al.
Pubblicazione: (2025)

From Reviewers' Lens: Understanding Bug Bounty Report Invalid Reasons with LLMs
di: Zheng, Jiangrui, et al.
Pubblicazione: (2025)

Models Are Codes: Towards Measuring Malicious Code Poisoning Attacks on Pre-trained Model Hubs
di: Zhao, Jian, et al.
Pubblicazione: (2024)

A Large-scale Empirical Study on the Generalizability of Disclosed Java Library Vulnerability Exploits
di: Chen, Zirui, et al.
Pubblicazione: (2026)

SCRUTINEER: Detecting Logic-Level Usage Violations of Reusable Components in Smart Contracts
di: Lin, Xingshuang, et al.
Pubblicazione: (2025)

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

Semantic Consensus Decoding: Backdoor Defense for Verilog Code Generation
di: Yang, Guang, et al.
Pubblicazione: (2026)

We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems
di: Li, Zhihao, et al.
Pubblicazione: (2025)

DLAP: A Deep Learning Augmented Large Language Model Prompting Framework for Software Vulnerability Detection
di: Yang, Yanjing, et al.
Pubblicazione: (2024)

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning
di: Huang, Charoes, et al.
Pubblicazione: (2026)

Coca: Improving and Explaining Graph Neural Network-Based Vulnerability Detection Systems
di: Cao, Sicong, et al.
Pubblicazione: (2024)

SCALE: Constructing Structured Natural Language Comment Trees for Software Vulnerability Detection
di: Wen, Xin-Cheng, et al.
Pubblicazione: (2024)

SolPhishHunter: Towards Detecting and Understanding Phishing on Solana
di: Li, Ziwei, et al.
Pubblicazione: (2025)

Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection
di: Li, Yikun, et al.
Pubblicazione: (2026)