Experimental Security Analyses of Access of Browser Extensions Accessing Sensitive Input Fields

Asmit Nayak, Rishabh Khandelwal, Earlence Fernandes, Kassem Fawaz

Keywords: browser extensions, data stealing, browser security risk

Abstract: Browser extensions offer a variety of valuable features and functionalities. They also pose a significant security risk if not properly designed or reviewed. Prior works have shown that browser extensions can access and manipulate data fields, including sensitive data such as passwords, credit card numbers, and Social Security numbers. In this paper, we present an empirical study of the security risks posed by browser extensions. Specifically, we first build a proof-of-concept extension that can steal sensitive user information. We find that the extension passes the Chrome webstore review process. We then perform a measurement study on the top 10K website login pages to check if the extension access to password fields via JS. We find that none of the password fields are actively protected, and can be accessed using JS. Moreover, we found that 1K websites store passwords in plaintext in their page source, including popular websites like \texttt{Google.com} and \texttt{Cloudflare.com}. We also analyzed over 160K Chrome Web Store extensions for malicious behavior, finding that 28K have permission to access sensitive fields and 190 store password fields in variables. To analyze the behavioral workflow of the potentially malicious extensions, we propose an LLM-driven framework, \textit{Extension Reviewer}. Finally, we discuss two countermeasures to address these risks: a bolt-on JavaScript package for immediate adoption by website developers allowing them to protect sensitive input fields, and a browser-level solution that alerts users when an extension accesses sensitive input fields. Our research highlights the urgent need for improved security measures to protect sensitive user information online.

Track: Responsible Web

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: Yes

Submission Number: 2235