Related papers: MCP-SandboxScan: WASM-based Secure Execution and R…
Large Language Models (LLMs) are increasingly serving as autonomous agents, and their utilization of external tools via the Model Context Protocol (MCP) is considered a future trend. Current MCP evaluation sets suffer from issues such as…
Equipping LLM agents with real-world tools can substantially improve productivity. However, granting agents autonomy over tool use also transfers the associated privileges to both the agent and the underlying LLM. Improper privilege usage…
Online malware scanners are one of the best weapons in the arsenal of cybersecurity companies and researchers. A fundamental part of such systems is the sandbox that provides an instrumented and isolated environment (virtualized or…
Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol (MCP). This extension could introduce new security vulnerabilities. We present a…
Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also…
Autonomous web agents such as \textbf{OpenClaw} are rapidly moving into high-impact real-world workflows, but their security robustness under live network threats remains insufficiently evaluated. Existing benchmarks mainly focus on static…
The Model Context Protocol (MCP) has rapidly become a de facto standard for connecting LLM-based agents with external tools via reusable MCP servers. In practice, however, server selection and onboarding rely heavily on free-text tool…
Although Foundation Models (FMs), such as GPT-4, are increasingly used in domains like finance and software engineering, reliance on textual interfaces limits these models' real-world interaction. To address this, FM providers introduced a…
The Model Context Protocol (MCP) is a recently proposed interoperability standard that unifies how AI agents connect with external tools and data sources. By defining a set of common client-server message exchange clauses, MCP replaces…
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…
The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such…
Recent large language models (LLMs) advancements sparked a growing research interest in tool assisted LLMs solving real-world challenges, which calls for comprehensive evaluation of tool-use capabilities. While previous works focused on…
AI agents increasingly run untrusted code on developer machines: shell commands generated by language models, third-party scripts retrieved at runtime, and tool plugins of unknown provenance. Existing isolation mechanisms impose tradeoffs…
Large Language Models (LLMs) are increasingly augmented with external tools through standardized interfaces like the Model Context Protocol (MCP). However, current MCP implementations face critical limitations: they typically require local…
AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agent's syscalls -- privileged operations with side effects on shared state -- yet today's safety…
Large Language Models (LLMs) increasingly rely on external tools to perform complex, realistic tasks, yet their ability to utilize the rapidly expanding Model Contextual Protocol (MCP) ecosystem remains limited. Existing MCP research covers…
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…
Tool calling has emerged as a critical capability for AI agents. In contrast to conventional tool calling frameworks that rely on static, provider-specific tool definitions, the Model Context Protocol (MCP) offers a unified interface to…
The Model Context Protocol (MCP) is emerging as a standard interface through which large language model (LLM) agents discover and invoke external tools. However, existing MCP evaluations fall short along three key axes: realistic multi-step…
The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which…