Related papers: Malicious Agent Skills in the Wild: A Large-Scale …

LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating software development, may exhibit unsafe behaviors during normal…

Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both…

When an LLM agent reads a confidential file, then writes a summary, then emails it externally, no single step is unsafe, but the sequence is a data leak. We call this safety drift: individually safe actions compounding into violations.…

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…

Healthcare automation is shaped by local procedures and organizational constraints, so agent capabilities rarely transfer unchanged across settings. Agent skills, self-contained directories that package reusable procedures for AI agents,…

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…

Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill…

This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful…

Coding agents, which are LLM-driven agents specialized in software development, have become increasingly prevalent in modern programming environments. Unlike traditional AI coding assistants, which offer simple code completion and…

Autonomous AI agents can now programmatically hire human workers through marketplaces using REST APIs and Model Context Protocol (MCP) integrations. This creates an attack surface analogous to CAPTCHA-solving services but with…

We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…

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…

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs…

Large language models (LLMs) are increasingly deployed through open-source and commercial frameworks, enabling individuals and organizations to self-host advanced LLM capabilities. As LLM deployments become prevalent, particularly in…

Modern software package registries like PyPI have become critical infrastructure for software development, but are increasingly exploited by threat actors distributing malicious packages with sophisticated multi-stage attack chains. While…

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static,…

Autonomous agents based on large language models (LLMs) are rapidly emerging as a general-purpose technology, with recent systems such as OpenClaw extending their capabilities through broad tool use, third-party skills, and deeper…

AI agents have significant potential to reshape cybersecurity, making a thorough assessment of their capabilities critical. However, existing evaluations fall short, because they are based on small-scale benchmarks and only measure static…