“the planner-executor isolation point is what stood out to me. right now most browser agent frameworks treat the LLM as both the decision-maker and the one processing untrusted content — so a prompt injection in page content can hijack the entire control flow. the paper's recommendation to split planning (trusted inputs only) from execution (handles untru…”
The Hidden Dangers of Browsing AI Agents
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. This paper presents a comprehensive security evaluation of such agents, focusing on systemic vulnerabilities across multiple architectural layers. Our work outlines the first end-to-end threat model for browsing agents and provides actionable guidance for securing their deployment in real-world environments. To address discovered threats, we propose a defense in depth strategy incorporating input sanitization, planner executor isolation, formal analyzers, and session safeguards. These measures protect against both initial access and post exploitation attack vectors. Through a white box analysis of a popular open source project, Browser Use, we demonstrate how untrusted web content can hijack agent behavior and lead to critical security breaches. Our findings include prompt injection, domain validation bypass, and credential exfiltration, evidenced by a disclosed CVE and a working proof of concept exploit.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)- The Dangers of Browsing AI Agents ↗walterbell · 2025-05-21 · 2 分
- The Dangers of Browsing AI Agents ↗wslh · 2025-05-24 · 2 分
- Security audit of Browser Use: prompt injection, credential exfil, domain bypass ↗tiny-automates · 2026-02-10 · 2 分