Related papers: OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runt…

Control-flow hijacking attacks manipulate orchestration mechanisms in multi-agent systems into performing unsafe actions that compromise the system and exfiltrate sensitive information. Recently proposed defenses, such as LlamaFirewall,…

The rise of Large Language Model (LLM) agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies…

Large language model (LLM) agents extend generative models with reasoning, tool use, and persistent memory, thereby enabling the automation of complex tasks. In healthcare, such systems could support documentation, care coordination, and…

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external…

We present OnPrem$.$LLM, a Python-based toolkit for applying large language models (LLMs) to sensitive, non-public data in offline or restricted environments. The system is designed for privacy-preserving use cases and provides prebuilt…

We introduce Llama Guard, an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks found in LLM…

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…

Existing LLM agents for computational materials science are constrained by pipeline-bounded architectures tied to specific simulation codes and by dependence on manually written tool functions that grow with task scope. We present MatClaw,…

Large Language Model (LLM) agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function…

Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parameter updates, and reusable components opens entry points for attackers. Threats have…

Large language models (LLMs) have proven to work well in question-answering scenarios, but real-world applications often require access to tools for live information or actuation. For this, LLMs can be extended with tools, which are often…

As the frequency of cyber threats increases, conventional penetration testing is failing to capture the entirety of todays complex environments. To solve this problem, we propose the Vulnerability Mitigation System (VMS), a novel agent…

Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such as prompt injection or memory poisoning. In deployment,…

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…

Large Language Models (LLMs) show promise in generating firmware for embedded systems, but often introduce security flaws and fail to meet real-time performance constraints. This paper proposes a three-phase methodology that combines…

Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to both answer accuracy and serving cost. Existing approaches either expand the context window…

Tool selection is a key component of LLM agents. A popular approach follows a two-step process - \emph{retrieval} and \emph{selection} - to pick the most appropriate tool from a tool library for a given task. In this work, we introduce…

LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at release time and grade mainly the final response, making it…

Large language model (LLM) agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers. These routers operate as application-layer proxies with full plaintext access to every…