Cover Image

Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hou, Xinyi, Zhao, Yanjie, Wang, Haoyu
Format:	Preprint
Published:	2026
Subjects:	Software Engineering
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Voices from the Frontier: A Comprehensive Analysis of the OpenAI Developer Forum
by: Hou, Xinyi, et al.
Published: (2024)

LLM Applications: Current Paradigms and the Next Frontier
by: Hou, Xinyi, et al.
Published: (2025)

LLM App Store Analysis: A Vision and Roadmap
by: Zhao, Yanjie, et al.
Published: (2024)

GPTZoo: A Large-scale Dataset of GPTs for the Research Community
by: Hou, Xinyi, et al.
Published: (2024)

Large Language Model Supply Chain: A Research Agenda
by: Wang, Shenao, et al.
Published: (2024)

Toward Understanding Bugs in Vector Database Management Systems
by: Xie, Yinglin, et al.
Published: (2025)

GPT Store Mining and Analysis
by: Su, Dongxun, et al.
Published: (2024)

Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead
by: Rao, Hongzhou, et al.
Published: (2025)

CommitSuite: A Comprehensive Benchmark for Commit Classification and Message Generation
by: Wan, Zirui, et al.
Published: (2026)

Bridging Design and Development with Automated Declarative UI Code Generation
by: Zhou, Ting, et al.
Published: (2024)

Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study
by: Hou, Xinyi, et al.
Published: (2025)

Towards Reliable Vector Database Management Systems: A Software Testing Roadmap for 2030
by: Wang, Shenao, et al.
Published: (2025)

Same App, Different Behaviors: Uncovering Device-specific Behaviors in Android Apps
by: Dong, Zikan, et al.
Published: (2024)

LaQual: A Novel Framework for Automated Evaluation of LLM App Quality
by: Wang, Yan, et al.
Published: (2025)

WaDec: Decompiling WebAssembly Using Large Language Model
by: She, Xinyu, et al.
Published: (2024)

CodeMorph: Mitigating Data Leakage in Large Language Model Assessment
by: Rao, Hongzhou, et al.
Published: (2025)

AUTOVR: Automated UI Exploration for Detecting Sensitive Data Flow Exposures in Virtual Reality Apps
by: Kim, John Y., et al.
Published: (2025)

Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
by: Ke, Qiang, et al.
Published: (2026)

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

Agent-Based Software Artifact Evaluation
by: Wu, Zhaonan, et al.
Published: (2026)

Understanding Large Language Model Supply Chain: Structure, Domain, and Vulnerabilities
by: Hu, Yanzhe, et al.
Published: (2025)

A Dual-Loop Agent Framework for Automated Vulnerability Reproduction
by: Liu, Bin, et al.
Published: (2026)

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

Fearless Unsafe. A More User-friendly Document for Unsafe Rust Programming Base on Refined Safety Properties
by: Cui, Mohan, et al.
Published: (2024)

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

Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification
by: Wu, Zehao, et al.
Published: (2025)

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

Adapting Installation Instructions in Rapidly Evolving Software Ecosystems
by: Gao, Haoyu, et al.
Published: (2023)

Large Language Models for Software Engineering: A Systematic Literature Review
by: Hou, Xinyi, et al.
Published: (2023)

CommitShield: Tracking Vulnerability Introduction and Fix in Version Control Systems
by: Wu, Zhaonan, et al.
Published: (2025)

Towards Robust Detection of Open Source Software Supply Chain Poisoning Attacks in Industry Environments
by: Zheng, Xinyi, et al.
Published: (2024)

Hidden Licensing Risks in the LLMware Ecosystem
by: Wang, Bo, et al.
Published: (2026)

Towards a Declarative Agentic Layer for Intelligent Agents in MCP-Based Server Ecosystems
by: Rodriguez-Sanchez, Maria Jesus, et al.
Published: (2026)

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

Unsafe and Unused? A History of Utility Code in Mature Open Source Projects
by: Keller, Brandon, et al.
Published: (2026)

FlowETL: An Autonomous Example-Driven Pipeline for Data Engineering
by: Di Profio, Mattia, et al.
Published: (2025)

How Agentic AI Coding Assistants Become the Attacker's Shell
by: Liu, Yue, et al.
Published: (2026)

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

Track and Trace: Automatically Uncovering Cross-chain Transactions in the Multi-blockchain Ecosystems
by: Lin, Dan, et al.
Published: (2025)

Understanding Software Vulnerabilities in the Maven Ecosystem: Patterns, Timelines, and Risks
by: Rabbi, Md Fazle, et al.
Published: (2025)