arXiv SecurityArchived Jun 15, 2026✓ Full text saved
arXiv:2606.14027v1 Announce Type: new Abstract: 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
Full text archived locally
✦ AI Summary· Claude Sonnet
Computer Science > Cryptography and Security
[Submitted on 12 Jun 2026]
Same-Origin Policy for Agentic Browsers
Xilong Wang, Xiaoxing Chen, Patrick Li, Dawn Song, Neil Gong
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 this https URL.
Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Systems and Control (eess.SY)
Cite as: arXiv:2606.14027 [cs.CR]
(or arXiv:2606.14027v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2606.14027
Focus to learn more
Submission history
From: Xilong Wang [view email]
[v1] Fri, 12 Jun 2026 02:01:38 UTC (7,587 KB)
Access Paper:
view license
Current browse context:
cs.CR
< prev | next >
new | recent | 2026-06
Change to browse by:
cs
cs.AI
cs.CL
cs.SY
eess
eess.SY
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Export BibTeX Citation
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Demos
Related Papers
About arXivLabs
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)