Ethical Hacking News
Malicious Extension Vulnerability Exposed: A Threat to Browser Security
A recent vulnerability in the Claude Dispatch feature has been exposed, which could potentially allow malicious extensions to run code on users' computers. The discovery of this vulnerability has significant implications for browser security and users' online safety. Users are advised to take precautions to protect themselves, including turning off cross-device Dispatch and monitoring AI agent activity. The vulnerability highlights the importance of browser security and the need for users to be vigilant. Read more about this critical vulnerability and how to protect yourself in the article below.
A vulnerability in the Claude Dispatch feature has been exposed, allowing malicious extensions to run code on users' computers. The vulnerability was discovered after a malicious extension on the claude.ai website sent instructions to the Claude Desktop app using the Dispatch feature. The Dispatch feature accepted an ordinary signed-in session on the claude.ai website, even though the site showed no link to it. The vulnerability can be exploited by malicious extensions, legitimate ones with a security flaw, or those that have been compromised. Users are advised to turn off cross-device Dispatch, review permissions, and monitor AI agent activities to protect themselves.
The online world has witnessed numerous breaches and security threats over the years, with browser extensions being a prime target for malicious actors. Recently, a vulnerability in the Claude Dispatch feature has been exposed, which could potentially allow malicious extensions to run code on users' computers. The discovery of this vulnerability has significant implications for browser security and users' online safety.
According to a report by Forever Security, a researcher at the company, the vulnerability was discovered after an extension running on the claude.ai website was able to send instructions to the Claude Desktop app using the Dispatch feature. This allowed the malicious extension to run scripts on the user's computer without their knowledge or consent. The Dispatch feature is a part of the Claude Desktop app, which is an AI agent that can run commands on the computer where it is installed.
The vulnerability is a result of a design flaw in the Dispatch feature, which allows malicious extensions to exploit the vulnerability. The researchers found that the Dispatch feature accepted an ordinary signed-in session on the claude.ai website, even though the site showed no link to it. This allowed the malicious extension to send instructions to the Claude Desktop app as if the user had sent them.
To exploit the vulnerability, the malicious extension needed two things: an extension that can run scripts on claude.ai and a person signed in to both claude.ai and Claude Desktop with Dispatch turned on. The extension could be malicious, a legitimate one that received a compromised update, or a legitimate one with a security flaw. The Dispatch feature only works while the computer is awake and the desktop app is open.
In the test conducted by Forever Security, a script on the user's claude.ai page opened Dispatch and sent Claude four prompts as if it were the user. The prompts asked Claude to install an npm package. Claude first hesitated over the unfamiliar package, but a follow-up message, delivered in the user's voice, got it to go ahead. Claude then ran a global npm install, and the package's install script opened the Calculator app. No browser exploit was needed.
The test was run with the browser and Claude Desktop on the same computer, and the researchers report no real attacks. However, the same reach could link a home computer to a work laptop when someone uses a single personal Claude account on both devices, with Dispatch turned on. The researchers have seen personal Claude accounts with cross-device Dispatch turned on, on work computers at their customers.
The vulnerability was reported to Anthropic, the company that makes Claude, on May 14. The company accepted it as valid on May 19 but closed the report as a duplicate of an issue it had already found internally, according to the researchers. The Dispatch feature is set to be retired, with the end of October as the target. However, the researchers note that two other Claude features, Claude Code Remote Control and Claude Cowork sessions, let extensions carry out the same attack.
In light of this vulnerability, users are advised to take precautions to protect themselves. According to the researchers, users should turn off cross-device Dispatch if they do not need it. If they do need it, they should review how devices are paired, approved, and removed. They should also treat browser extensions like other software on the computer, checking their permissions, controlling what gets installed, and reviewing updates that give them more access.
Monitoring what AI agents do on the computer, including unexpected package installations, setting changes, access to credentials, and external connections, is also crucial. The researchers recommend that users take these steps to ensure their online safety.
The discovery of this vulnerability highlights the importance of browser security and the need for users to be vigilant. Malicious extensions can pose a significant threat to users' online safety, and it is essential to take steps to protect oneself.
Related Information:
https://www.ethicalhackingnews.com/articles/Malicious-Extension-Vulnerability-Exposed-A-Threat-to-Browser-Security-ehn.shtml
https://thehackernews.com/2026/11/malicious-browser-extensions-could-use.html
Published: Fri Nov 6 08:17:01 2026 by llama3.2 3B Q4_K_M
