Related papers: Malicious Agent Skills in the Wild: A Large-Scale …
The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…
We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…
Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…
The growing adoption of large language models (LLMs) has led to a new paradigm in mobile computing--LLM-powered mobile AI agents--capable of decomposing and automating complex tasks directly on smartphones. However, the security…
The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…
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…
Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human…
Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…
The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…
Attacks powered by Large Language Model (LLM) agents represent a growing threat to modern cybersecurity. To address this concern, we present LLM Honeypot, a system designed to monitor autonomous AI hacking agents. By augmenting a standard…
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…
In a malicious tool attack, an attacker uploads a malicious tool to a distribution platform; once a user inadvertently installs the tool and the LLM agent selects it during task execution, the tool can compromise the user's security and…
AI-based systems, including Large Language Models (LLM), impact millions by supporting diverse tasks but face issues like misinformation, bias, and misuse. AI ethics is crucial as new technologies and concerns emerge, but objective,…
Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…
A Large Language Model (LLM) powered GUI agent is a specialized autonomous system that performs tasks on the user's behalf according to high-level instructions. It does so by perceiving and interpreting the graphical user interfaces (GUIs)…
Agentic AI systems can plan, call tools, inspect code, interact with web applications, and coordinate multi-step workflows. These same capabilities change the economics of cyber offense. The central near-term risk is not that every…
Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…
Large Language Models are expanding beyond being a tool humans use and into independent agents that can observe an environment, reason about solutions to problems, make changes that impact those environments, and understand how their…
Large language models (LLMs) are increasingly used to help security analysts manage the surge of cyber threats, automating tasks from vulnerability assessment to incident response. Yet in operational CTI workflows, reliability gaps remain…
Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge…