Related papers: Towards Secure Agent Skills: Architecture, Threat …
Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to…
Advances in large language models have enabled agentic AI systems that can reason, plan, and interact with external tools to execute multi-step workflows, while public blockchains have evolved into a programmable substrate for value…
As large language models are integrated into autonomous robotic systems for task planning and control, compromised inputs or unsafe model outputs can propagate through the planning pipeline to physical-world consequences. Although prior…
Agent Skills package SKILL.md files, scripts, reference documents, and repository context into reusable capability units, turning pre-load auditing from single-prompt filtering into cross-file security review. Existing guardrails often flag…
Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy…
Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound capabilities in collective intelligence. However, the potential misuse of this intelligence for malicious purposes presents significant risks. To date,…
LLM-based agents have recently attracted significant attention due to their ability to autonomously invoke relevant tools to accomplish complex tasks. However, recent studies have shown that these agents face severe security risks, which…
This paper introduces a multi-agent framework guided by Large Language Models (LLMs) to assist in the early stages of engineering design, a phase often characterized by vast parameter spaces and inherent uncertainty. Operating under a…
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…
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…
Agent skills - structured packages of instructions, scripts, and references that augment a large language model (LLM) without modifying the model itself - have moved from convenience to first-class deployment artifact. The runtime that…
Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…
The rapid evolution of Large Language Models (LLM) and subsequent Agentic AI technologies requires systematic architectural guidance for building sophisticated, production-grade systems. This paper presents an approach for architecting such…
The rapid integration of Large Language Models (LLMs) across diverse sectors has marked a transformative era, showcasing remarkable capabilities in text generation and problem-solving tasks. However, this technological advancement is…
Users often interpret and select agent skills through their SKILL markdown specifications. To protect users, existing audits mainly focus on malicious or unsafe skills. We study the complementary question of whether specifications help…
Agent Skills have become a practical way to extend LLM agents by packaging metadata, natural-language instructions, and executable resources into reusable capability bundles. However, this growing Skill ecosystem introduces a new compliance…
The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. However, the evolving nature of…
Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation, and analysis tasks. However, the term "data agent" is currently used inconsistently, conflating…
We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens,…
This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a structural consequence of how agent execution works, not a…