Image de couverture de livre

Parasites in the Toolchain: A Large-Scale Analysis of Attacks on the MCP Ecosystem

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Shuli, Hou, Qinsheng, Zhan, Zihan, Wang, Yanhao, Xie, Yuchong, Guo, Yu, Chen, Libo, Li, Shenghong, Xue, Zhi
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem
par: Song, Hao, et autres
Publié: (2025)

CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
par: Liu, Zesen, et autres
Publié: (2025)

A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis
par: Lin, Zhiwei, et autres
Publié: (2025)

MCP Pitfall Lab: Exposing Developer Pitfalls in MCP Tool Server Security under Multi-Vector Attacks
par: Hao, Run, et autres
Publié: (2026)

When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation
par: Zhao, Weibo, et autres
Publié: (2025)

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
par: Zhang, Zhixiang, et autres
Publié: (2026)

AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on Edge Devices
par: Zhan, Zhonghao, et autres
Publié: (2025)

We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems
par: Li, Zhihao, et autres
Publié: (2025)

PrivAgE: A Toolchain for Privacy-Preserving Distributed Aggregation on Edge-Devices
par: Liebenow, Johannes, et autres
Publié: (2023)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
par: Wang, Libo
Publié: (2024)

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
par: Hou, Xinyi, et autres
Publié: (2025)

When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
par: Luo, Mingyu, et autres
Publié: (2026)

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
par: Zhang, Shenyi, et autres
Publié: (2025)

MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools
par: Tan, Zhuoran, et autres
Publié: (2026)

A Lightweight Authentication Protocol against Modeling Attacks based on a Novel LFSR-APUF
par: Wang, Yao, et autres
Publié: (2023)

ZTaint-Havoc: From Havoc Mode to Zero-Execution Fuzzing-Driven Taint Inference
par: Xie, Yuchong, et autres
Publié: (2025)

SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization
par: Zhang, Hao, et autres
Publié: (2025)

Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
par: Wang, Xiangwen, et autres
Publié: (2026)

External Data Extraction Attacks against Retrieval-Augmented Large Language Models
par: He, Yu, et autres
Publié: (2025)

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems
par: Maloyan, Narek, et autres
Publié: (2026)

MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers
par: Wang, Zhiqiang, et autres
Publié: (2025)

"MCP Does Not Stand for Misuse Cryptography Protocol": Uncovering Cryptographic Misuse in Model Context Protocol at Scale
par: Yan, Biwei, et autres
Publié: (2025)

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
par: Wang, Zihan, et autres
Publié: (2026)

Poisoning Attacks to Local Differential Privacy for Ranking Estimation
par: Zhan, Pei, et autres
Publié: (2025)

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models
par: Wang, Zihan, et autres
Publié: (2026)

MCPGuard : Automatically Detecting Vulnerabilities in MCP Servers
par: Wang, Bin, et autres
Publié: (2025)

Shrinking the Kernel Attack Surface Through Static and Dynamic Syscall Limitation
par: Zhan, Dongyang, et autres
Publié: (2025)

A Toolchain for Assisting Migration of Software Executables Towards Post-Quantum Cryptography
par: Rattanavipanon, Norrathep, et autres
Publié: (2024)

Safeguarding Blockchain Ecosystem: Understanding and Detecting Attack Transactions on Cross-chain Bridges
par: Wu, Jiajing, et autres
Publié: (2024)

MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP
par: Li, Ruiqi, et autres
Publié: (2026)

FOX: Coverage-guided Fuzzing as Online Stochastic Control
par: She, Dongdong, et autres
Publié: (2024)

Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
par: Fu, Hang, et autres
Publié: (2026)

Exploring and Exploiting the Resource Isolation Attack Surface of WebAssembly Containers
par: Yu, Zhaofeng, et autres
Publié: (2025)

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
par: Zhang, Dongsen, et autres
Publié: (2025)

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
par: Liu, Shi, et autres
Publié: (2026)

MCP-in-SoS: Risk assessment framework for open-source MCP servers
par: Kumar, Pratyay, et autres
Publié: (2026)

Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models
par: Wen, Jinming, et autres
Publié: (2025)

A Large-scale Fine-grained Analysis of Packages in Open-Source Software Ecosystems
par: Zhou, Xiaoyan, et autres
Publié: (2024)

TZ-LLM: Protecting On-Device Large Language Models with Arm TrustZone
par: Wang, Xunjie, et autres
Publié: (2025)

Securing the Model Context Protocol (MCP): Risks, Controls, and Governance
par: Errico, Herman, et autres
Publié: (2025)