Related papers: MCP-ITP: An Automated Framework for Implicit Tool …

This paper presents Poisoning MorphNet, the first backdoor attack method on point clouds. Conventional adversarial attack takes place in the inference stage, often fooling a model by perturbing samples. In contrast, backdoor attack aims to…

Deterministic model predictive control (MPC), while powerful, is often insufficient for effectively controlling autonomous systems in the real-world. Factors such as environmental noise and model error can cause deviations from the expected…

We investigate the problem of designing optimal stealthy poisoning attacks on the control channel of Markov decision processes (MDPs). This research is motivated by the recent interest of the research community for adversarial and poisoning…

Agentic workflows driven by large language models (LLMs) are increasingly applied to Building Information Modelling (BIM), enabling natural-language retrieval, modification and generation of IFC models. Recent work has begun adopting the…

Model Context Protocol (MCP) servers contain a collection of thousands of open-source standardized tools, linking LLMs to external systems; however, existing datasets and benchmarks lack realistic, human-like user queries, remaining a…

Recent research has explored that LLM agents are vulnerable to indirect prompt injection (IPI) attacks, where malicious tasks embedded in tool-retrieved information can redirect the agent to take unauthorized actions. Existing defenses…

LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which…

Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform…

Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination underpinning contemporary production systems. We study a previously unexamined failure of this…

With advances in decision-making and reasoning capabilities, multimodal agents show strong potential in computer application scenarios. Past evaluations have mainly assessed GUI interaction skills, while tool invocation abilities, such as…

The integration of artificial intelligence into automated penetration testing (AutoPT) has highlighted the necessity of simulation modeling for the training of intelligent agents, due to its cost-efficiency and swift feedback capabilities.…

This paper introduces Agentic-AI Healthcare, a privacy-aware, multilingual, and explainable research prototype developed as a single-investigator project. The system leverages the emerging Model Context Protocol (MCP) to orchestrate…

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…

Industrial cyber-physical systems (ICPS) are gradually integrating information technology and automating industrial processes, leading systems to become more vulnerable to malicious actors. Thus, to deploy secure Industrial Control and…

AI development environments are evolving into observability first platforms that integrate real time telemetry, prompt traces, and evaluation feedback into the developer workflow. This paper introduces telemetry aware integrated development…

Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that spans websites and sessions. While existing…

As Large Language Models (LLMs) grow increasingly powerful, multi-agent systems are becoming more prevalent in modern AI applications. Most safety research, however, has focused on vulnerabilities in single-agent LLMs. These include prompt…

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting…

Agent skills are increasingly used to extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources. While improving reusability, this modular design also introduces a new supply-chain attack surface: a…