Related papers: Skill-Inject: Measuring Agent Vulnerability to Ski…
Large Language Models (LLMs) are combined with tools to create powerful LLM agents that provide a wide range of services. Unlike traditional software, LLM agent's behavior is determined at runtime by natural language prompts from either…
As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…
Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or…
Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within a candidate document (i.e., jailbreak prompt attacks) can significantly alter an LLM's…
Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…
Attacks powered by Large Language Model (LLM) agents represent a growing threat to modern cybersecurity. To address this concern, we present LLM Honeypot, a system designed to monitor autonomous AI hacking agents. By augmenting a standard…
Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…
Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…
As LLM agents transition from digital assistants to physical controllers in autonomous systems and robotics, they face an escalating threat from indirect prompt injection. By embedding adversarial instructions into the results of tool…
Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to active system interaction and environment management. OpenClaw, a representative platform…
LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges…
Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…
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…
Command injection vulnerabilities are a significant security threat in dynamic languages like Python, particularly in widely used open-source projects where security issues can have extensive impact. With the proven effectiveness of Large…
Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…
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 frontier language models are increasingly deployed as autonomous agents pursuing complex, long-term objectives, there is increased risk of scheming: agents covertly pursuing misaligned goals. Prior work has focused on showing agents are…
The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web…
Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…
Agentic computing systems, while immensely capable, raise serious security, privacy, and safety concerns. A key issue is that the full set of functionalities offered by these systems, combined with their probabilistic execution flows, is…