Related papers: LivePI: More Realistic Benchmarking of Agents Agai…

Recent work has embodied LLMs as agents, allowing them to access tools, perform actions, and interact with external content (e.g., emails or websites). However, external content introduces the risk of indirect prompt injection (IPI)…

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model…

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…

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose…

Modern coding agents integrated into IDEs orchestrate powerful tools and high-privilege system access, creating a high-stakes attack surface. Prior work on Indirect Prompt Injection (IPI) is mainly query-specific, requiring particular user…

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…

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

This report presents a real-world case study demonstrating how prompt injection can attack large language model platforms such as ChatGPT according to a proposed injection framework. By providing three real-world examples, we show how…

Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…

LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination…

Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions…

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 model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching…

Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden instructions in the HTML pages those domains serve. Existing…

With the fast development of large language models (LLMs), LLM-driven Web Agents (Web Agents for short) have obtained tons of attention due to their superior capability where LLMs serve as the core part of making decisions like the human…

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security…

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…

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…

The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection attacks. In these attacks, malicious instructions embedded…

Large Language Model (LLM) agents exhibit remarkable performance across diverse applications by using external tools to interact with environments. However, integrating external tools introduces security risks, such as indirect prompt…