Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shen, Yulin, Pan, Xudong, Hong, Geng, Yang, Min
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MCPThreatHive: Automated Threat Intelligence for Model Context Protocol Ecosystems
by: Shen, Yi Ting, et al.
Published: (2026)

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models
by: Xiong, Junjie, et al.
Published: (2025)

StruPhantom: Evolutionary Injection Attacks on Black-Box Tabular Agents Powered by Large Language Models
by: Feng, Yang, et al.
Published: (2025)

SentinelNet: Safeguarding Multi-Agent Collaboration Through Credit-Based Dynamic Threat Detection
by: Feng, Yang, et al.
Published: (2025)

MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent
by: Wu, Mengying, et al.
Published: (2025)

MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0)
by: Shen, Yi Ting, et al.
Published: (2026)

Invisible to Humans, Triggered by Agents: Stealthy Jailbreak Attacks on Mobile Vision-Language Agents
by: Ding, Renhua, et al.
Published: (2025)

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
by: Cao, Yuanpu, et al.
Published: (2023)

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
by: Hou, Xinyi, et al.
Published: (2025)

From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
by: Ferrag, Mohamed Amine, et al.
Published: (2025)

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
by: Maloyan, Narek, et al.
Published: (2026)

PRISON: Unmasking the Criminal Potential of Large Language Models
by: Wu, Xinyi, et al.
Published: (2025)

CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly
by: Fan, Yihe, et al.
Published: (2026)

WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents
by: Wu, Xinyi, et al.
Published: (2026)

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

Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered Graph Foundation Models
by: Xue, Xiaoyu, et al.
Published: (2025)

WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference
by: Xiong, Zixun, et al.
Published: (2026)

Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models
by: Ganiuly, Daniyal, et al.
Published: (2025)

Prompt Injection 2.0: Hybrid AI Threats
by: McHugh, Jeremy, et al.
Published: (2025)

Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
by: Geng, Jianing, et al.
Published: (2025)

ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models
by: Xu, Zhenhua, et al.
Published: (2026)

Towards Backdoor Stealthiness in Model Parameter Space
by: Xu, Xiaoyun, et al.
Published: (2025)

SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
by: Yang, He, et al.
Published: (2026)

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection
by: Debi, Tanusree, et al.
Published: (2026)

Invisible Textual Backdoor Attacks based on Dual-Trigger
by: Hou, Yang, et al.
Published: (2024)

Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications
by: Jiang, Changyue, et al.
Published: (2024)

Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models
by: Yang, Yiqi, et al.
Published: (2024)

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
by: Wang, Che, et al.
Published: (2026)

Payload-Aware Intrusion Detection with CMAE and Large Language Models
by: Kim, Yongcheol, et al.
Published: (2025)

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
by: Liu, Zhichao, et al.
Published: (2026)

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
by: Qiu, Huming, et al.
Published: (2023)

AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
by: Li, Changyi, et al.
Published: (2026)

Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
by: Lu, Yifan, et al.
Published: (2023)

Stealthy Backdoor Attack to Real-world Models in Android Apps
by: Wei, Jiali, et al.
Published: (2025)

Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing Detection
by: Koide, Takashi, et al.
Published: (2026)

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation
by: Zhang, Xiaoyu, et al.
Published: (2025)

Threat Modeling for Enhancing Security of IoT Audio Classification Devices under a Secure Protocols Framework
by: Benlloch-Lopez, Sergio, et al.
Published: (2025)

ThreatModeling-LLM: Automating Threat Modeling using Large Language Models for Banking System
by: Wu, Tingmin, et al.
Published: (2024)

Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem
by: Gaire, Shiva, et al.
Published: (2025)

MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols
by: Yang, Yixuan, et al.
Published: (2025)