Related papers: Hacking CTFs with Plain Agents

AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspired by the well-established concept of firewalls, we show…

With the continuous evolution of Large Language Models (LLMs), LLM-based agents have advanced beyond passive chatbots to become autonomous cyber entities capable of performing complex tasks, including web browsing, malicious code and…

Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are often unavailable…

Humans write code in a fundamentally interactive manner and rely on constant execution feedback to correct errors, resolve ambiguities, and decompose tasks. While LLMs have recently exhibited promising coding capabilities, current coding…

LLM Agents are becoming central to intelligent systems. However, their deployment raises serious safety concerns. Existing defenses largely rely on "Safety Checks", which struggle to capture the complex semantic risks posed by harmful user…

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated…

We present, to our knowledge, the most comprehensive cross-model evaluation of LLM agents on offensive cybersecurity tasks, benchmarking 10 frontier models from 7 providers on all 200 challenges of the NYU CTF Bench. Building on the…

Cyber threats are rapidly increasing, expanding their impact from large-scale enterprises to government services and individual users, making robust security systems increasingly essential. However, a significant shortage of skilled…

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…

Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…

Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense strategy tailored to counter LLM-driven cyberattacks.…

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an external environment; this makes them susceptible to prompt injections when dealing with untrusted data. To overcome this limitation, we propose…

This study evaluates the ability of GPT-4o to autonomously solve beginner-level offensive security tasks by connecting the model to OverTheWire's Bandit capture-the-flag game. Of the 25 levels that were technically compatible with a…

From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research…

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions,…

Cyber Threat Intelligence (CTI) reports document observations of cyber threats, synthesizing evidence about adversaries' actions and intent into actionable knowledge that informs detection, response, and defense planning. However, the…

Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from…