Same-Origin Policy for Agentic Browsers
Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instructions. The same-origin policy (SOP) is a fundamental browser security mechanism that prevents unauthorized automated cross-origin data flows induced by scripts. However, whether SOP remains effective in agentic browsers is an open question that has not been systematically studied. In this work, we bridge this gap. We first observe that an agentic browser can itself serve as an automated channel for cross-origin data flows, potentially leading to SOP violations. To investigate this phenomenon, we construct SOPBench, a benchmark for evaluating SOP violations in agentic browsers. Our evaluation shows that existing agentic browsers frequently violate SOP, both in benign settings and under attacks. To address this problem, we propose SOPGuard, an SOP enforcement mechanism tailored to agentic browsers. We implement SOPGuard in BrowserOS, an open-source agentic browser. Extensive evaluations demonstrate that SOPGuard effectively enforces SOP while preserving utility and incurring only a small runtime overhead. Our code and data are available at https://github.com/wxl-lxw/BrowserOS-SOPGuard.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers
Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where mal…
Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents
For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: does the desired safety refusal, typically…
ChatbotRed TeamingWebLLM: A High-Performance In-Browser LLM Inference Engine
Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source…
CPUGPUPrivacy PreservingAgentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories
Large Language Model (LLM) agents are commonly trained from expert trajectories using supervised fine-tuning (SFT), which treats multi-turn agent behavior as ordinary text imitation. This recipe is simple and low-cost, b…
Reinforcement LearningField Label Prediction for Autofill in Web Browsers
Automatic form fill is an important productivity related feature present in major web browsers, which predicts the field labels of a web form and automatically fills values in a new form based on the values previously fi…
BIG-bench Machine LearningFormPrediction