English
Related papers

Related papers: Penetration Testing of Agentic AI: A Comparative S…

200 papers

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

Artificial Intelligence · Computer Science 2026-04-07 Bowen Wei , Yunbei Zhang , Jinhao Pan , Kai Mei , Xiao Wang , Jihun Hamm , Ziwei Zhu , Yingqiang Ge

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on…

Cryptography and Security · Computer Science 2026-04-07 Charafeddine Mouzouni

The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…

Artificial Intelligence · Computer Science 2026-05-15 Yixu Wang , Xin Wang , Yang Yao , Xinyuan Li , Xibang Yang , Yan Teng , Xingjun Ma , Yingchun Wang

Previous benchmarks on prompt injection in large language models (LLMs) have primarily focused on generic tasks and attacks, offering limited insights into more complex threats like data exfiltration. This paper examines how prompt…

Cryptography and Security · Computer Science 2025-06-03 Meysam Alizadeh , Zeynab Samei , Daria Stetsenko , Fabrizio Gilardi

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…

Cryptography and Security · Computer Science 2026-05-25 Xueyi Li , Zhuoneng Zhou , Zitao Liu , Yongdong Wu

As large language models (LLMs) increasingly mediate emotionally sensitive conversations, especially in mental health contexts, their ability to recognize and respond to high-risk situations becomes a matter of public safety. This study…

Agentic AI systems exhibit numerous crosscutting concerns -- security, observability, cost management, fault tolerance -- that are poorly modularized in current implementations, contributing to the high failure rate of AI projects in…

Artificial Intelligence · Computer Science 2026-03-03 Yijun Yu

The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…

Software Engineering · Computer Science 2026-04-30 Happy Bhati

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…

Cryptography and Security · Computer Science 2026-04-22 Dongcheng Zhang , Yiqing Jiang

Agentic AI coding tools increasingly automate software development tasks. Developers can configure these tools through versioned repository-level artifacts such as Markdown and JSON files. We present a systematic analysis of configuration…

Prompt injection remains a central obstacle to the safe deployment of large language models, particularly in multi-agent settings where intermediate outputs can propagate or amplify malicious instructions. Building on earlier work that…

Artificial Intelligence · Computer Science 2026-01-21 Diego Gosmar , Deborah A. Dahl

Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results…

Artificial Intelligence · Computer Science 2026-03-19 Yuntong Zhang , Sungmin Kang , Ruijie Meng , Marcel Böhme , Abhik Roychoudhury

AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make…

Cryptography and Security · Computer Science 2026-04-24 Ari Azarafrooz

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…

Artificial Intelligence · Computer Science 2026-01-26 Donghao Huang , Gauri Malwe , Zhaoxia Wang

Do next-generation LLM agents inherit the cooperative biases documented in their predecessors, or does scale and provider diversity reshape equilibrium behaviour in competitive multi-agent settings? Willis et al. established a benchmark for…

Multiagent Systems · Computer Science 2026-05-29 Francisco León Zúñiga Bolívar

We present and evaluate a suite of proof-of-concept (PoC), structured workflow prompts designed to elicit human-like hierarchical reasoning while guiding Large Language Models (LLMs) in the high-level semantic and linguistic analysis of…

Computation and Language · Computer Science 2025-06-18 Evgeny Markhasin

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…

Cryptography and Security · Computer Science 2026-05-06 Shihao Weng , Yang Feng , Jinrui Zhang , Xiaofei Xie , Jiongchi Yu , Jia Liu

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…

Cryptography and Security · Computer Science 2026-05-07 Kexin Chu

Agentic AI represents a paradigm shift in enhancing the capabilities of generative AI models. While these systems demonstrate immense potential and power, current evaluation techniques primarily focus on assessing their efficacy in…

Artificial Intelligence · Computer Science 2025-09-30 Hassen Dhrif

Agentic AI coding editors driven by large language models have recently become more popular due to their ability to improve developer productivity during software development. Modern editors such as Cursor are designed not just for code…

Cryptography and Security · Computer Science 2026-04-29 Yue Liu , Yanjie Zhao , Yunbo Lyu , Ting Zhang , Haoyu Wang , David Lo