Related papers: IntentMiner: Intent Inversion Attack via Tool Call…

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due…

Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…

To reduce development overhead and enable seamless integration between potential components comprising any given generative AI application, the Model Context Protocol (MCP) (Anthropic, 2024) has recently been released and subsequently…

Model Context Protocol (MCP) has emerged as a standard interface for connecting LLM agents to external tools. Because MCP servers expose privileged operations such as shell execution, network access, and file-system manipulation to…

Large Language Models (LLMs) with tool-calling capabilities have demonstrated remarkable potential in executing complex tasks through external tool integration. The Model Context Protocol (MCP) has emerged as a standardized framework for…

With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse,…

The Model Context Protocol (MCP) enables large language models to invoke external tools through natural-language descriptions, forming the foundation of many AI agent applications. However, MCP does not enforce consistency between…

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…

Large Language Models (LLMs) have emerged as transformative tools for natural language understanding and user intent resolution, enabling tasks such as translation, summarization, and, increasingly, the orchestration of complex workflows.…

To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by…

The Model Context Protocol (MCP) enhances large language models (LLMs) by integrating external tools, enabling dynamic aggregation of real-time data to improve task execution. However, its non-isolated execution context introduces critical…

The Model Context Protocol (MCP), introduced by Anthropic in November 2024 and now governed by the Linux Foundation's Agentic AI Foundation, has rapidly become the de facto standard for connecting large language model (LLM)-based agents to…

Model Context Protocol (MCP) servers enable AI applications to connect to external systems in a plug-and-play manner, but their rapid proliferation also introduces severe security risks. Unlike mature software ecosystems with rigorous…

Large Language Models (LLMs) are increasingly integrated into real-world applications via the Model Context Protocol (MCP), a universal open standard for connecting AI agents with data sources and external tools. While MCP enhances the…

Large language model (LLM) agents increasingly rely on external tools and retrieval systems to autonomously complete complex tasks. However, this design exposes agents to indirect prompt injection (IPI), where attacker-controlled context…

The Model Context Protocol (MCP) is rapidly emerging as a pivotal open standard, designed to enhance agent-tool integration and interoperability, and is positioned to unlock a new era of powerful, interconnected, and genuinely utilitarian…

Large language models (LLMs) are evolving into agentic systems that reason, plan, and operate external tools. The Model Context Protocol (MCP) is a key enabler of this transition, offering a standardized interface for connecting LLMs with…

Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may…

Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense…

The Model Context Protocol (MCP), introduced by Anthropic, provides a standardized framework for artificial intelligence (AI) systems to interact with external data sources and tools in real-time. While MCP offers significant advantages for…