Imagen de Portada

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Huang, Charoes, Huang, Xin, Tran, Ngoc Phu, Fard, Amin Milani
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Software Engineering
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

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

MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security
por: Guo, Yongjian, et al.
Publicado: (2025)

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

Many Tools, Few Exploitable Vulnerabilities: A Survey of 246 Static Code Analyzers for Security
por: Hermann, Kevin, et al.
Publicado: (2026)

WACANA: A Concolic Analyzer for Detecting On-chain Data Vulnerabilities in WASM Smart Contracts
por: Wang, Wansen, et al.
Publicado: (2024)

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

Exploring the Security Threats of Knowledge Base Poisoning in Retrieval-Augmented Code Generation
por: Lin, Bo, et al.
Publicado: (2025)

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

LLM-Assisted Model-Based Fuzzing of Protocol Implementations
por: Huang, Changze, et al.
Publicado: (2025)

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
por: He, Ping, et al.
Publicado: (2025)

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

APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching
por: Nong, Yu, et al.
Publicado: (2024)

TPSQLi: Test Prioritization for SQL Injection Vulnerability Detection in Web Applications
por: Yang, Guan-Yan, et al.
Publicado: (2025)

Impact of Code Transformation on Detection of Smart Contract Vulnerabilities
por: Manh, Cuong Tran, et al.
Publicado: (2024)

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

Asset-centric Threat Modeling for AI-based Systems
por: von der Assen, Jan, et al.
Publicado: (2024)

ThreMoLIA: Threat Modeling of Large Language Model-Integrated Applications
por: Jedrzejewski, Felix Viktor, et al.
Publicado: (2025)

Threat Modelling and Risk Analysis for Large Language Model (LLM)-Powered Applications
por: Tete, Stephen Burabari
Publicado: (2024)

Uncover the Premeditated Attacks: Detecting Exploitable Reentrancy Vulnerabilities by Identifying Attacker Contracts
por: Yang, Shuo, et al.
Publicado: (2024)

Publish Your Threat Models! The benefits far outweigh the dangers
por: Kohnfelder, Loren, et al.
Publicado: (2025)

Security Is Relative: Training-Free Vulnerability Detection via Multi-Agent Behavioral Contract Synthesis
por: Wang, Yongchao, et al.
Publicado: (2026)

A LINDDUN-based Privacy Threat Modeling Framework for GenAI
por: Liao, Qianying, et al.
Publicado: (2026)

Vulnerability Detection in Popular Programming Languages with Language Models
por: Atiiq, Syafiq Al, et al.
Publicado: (2024)

Exposing and Defending Membership Leakage in Vulnerability Prediction Models
por: Liao, Yihan, et al.
Publicado: (2025)

"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
por: Liu, Yue, et al.
Publicado: (2025)

ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents
por: Wu, Jiangrong, et al.
Publicado: (2026)

Unity is Strength: Enhancing Precision in Reentrancy Vulnerability Detection of Smart Contract Analysis Tools
por: Wang, Zexu, et al.
Publicado: (2024)

Introducing Systems Thinking as a Framework for Teaching and Assessing Threat Modeling Competency
por: Joshi, Siddhant S., et al.
Publicado: (2024)

Game Rewards Vulnerabilities: Software Vulnerability Detection with Zero-Sum Game and Prototype Learning
por: Wen, Xin-Cheng, et al.
Publicado: (2024)

Evaluating Large Language Models for Line-Level Vulnerability Localization
por: Zhang, Jian, et al.
Publicado: (2024)

Vulnerability Detection with Interprocedural Context in Multiple Languages: Assessing Effectiveness and Cost of Modern LLMs
por: Lira, Kevin, et al.
Publicado: (2026)

HALURust: Exploiting Hallucinations of Large Language Models to Detect Vulnerabilities in Rust
por: Luo, Yu, et al.
Publicado: (2025)

Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap
por: Huang, Feiyang, et al.
Publicado: (2026)

Efficient Software Vulnerability Detection Using Transformer-based Models
por: Shaik, Sameer, et al.
Publicado: (2026)

Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
por: Li, Yikun, et al.
Publicado: (2025)

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

Revisiting Vulnerability Patch Identification on Data in the Wild
por: Irsan, Ivana Clairine, et al.
Publicado: (2026)

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

FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction
por: Sheng, Ze, et al.
Publicado: (2026)