Related papers: "What Did It Actually Do?": Understanding Risk Awa…

AI agents dynamically acquire tools, orchestrate sub-agents, and transact across organizational boundaries, yet no existing security layer verifies what an agent can do, whether it executed what it claims, or what happened in a multi-agent…

Introduction: The use of chatbots is becoming increasingly important across various aspects of daily life. However, the privacy concerns associated with these communications have not yet been thoroughly addressed. The aim of this study was…

Code agents powered by large language models can execute shell commands on behalf of users, introducing severe security vulnerabilities. This paper presents a two-phase security analysis of the OpenClaw platform. As an open-source AI agent…

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

Chatbots, the common moniker for collaborative assistants, are Artificial Intelligence (AI) software that enables people to naturally interact with them to get tasks done. Although chatbots have been studied since the dawn of AI, they have…

Tool-using agents often incur substantial computational cost due to long reasoning chains and iterative tool usage. In practical scenarios, many tasks become infeasible under constrained tool environments, where the capabilities required…

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or…

Assistive machines endow people with limited mobility the opportunity to live more independently. However, operating these machines poses risks to the safety of the human operator as well as the surrounding environment. Thus, proper user…

Individuals are increasingly relying on large language model (LLM)-enabled conversational agents for emotional support. While prior research has examined privacy and security issues in chatbots specifically designed for mental health…

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns that can discourage data sharing, limiting both the autonomy levels at which agents can operate and…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

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…

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…

In recent years, the landscape of software threats has become significantly more dynamic and distributed. Security vulnerabilities are no longer discovered and shared only through formal channels such as public vulnerability databases or…

When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful…

The widespread use of Large Language Model (LLM)-based conversational agents (CAs), especially in high-stakes domains, raises many privacy concerns. Building ethical LLM-based CAs that respect user privacy requires an in-depth understanding…

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

The rise of personal assistant agents, e.g., OpenClaw, highlights the growing potential of large language models to support users across everyday life and work. A core challenge in these settings is proactive assistance, since users often…