Claude Dispatch flaw can let browser extensions run system commands
Anthropic's Claude Dispatch contains a vulnerability that can let browser extensions direct Claude Desktop to run system commands, The Register reports. The attack can reach another computer signed into the same Claude account if Dispatch connects the devices.
Forever Security researcher Gal Weizman found that a browser extension with access to an authenticated Claude web session could issue commands through the Dispatch interface and API. The user must also be signed into Claude Desktop, while the relevant remote session must be available. His proof of concept used Claude to install a malicious npm package that opened the calculator application.
Anthropic recognized the report as a valid vulnerability in May but closed it as a duplicate of an existing issue. The company told Weizman it planned to retire Dispatch at the end of October, but its support page still listed the feature as available to existing users on October 30. Weizman said the same session sharing design is also present in Claude Code Remote Control and Claude Cowork.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Cybersecurity AI Weekly or Daily AI Brief.
Also, consider following us on social media:
More from Cybersecurity
Nov 5 Palo Alto Networks in Talks to Acquire Beacon Security Nov 5 Capgemini to Lead EU AI Cyber Risk Consortium Nov 5 Palo Alto Networks in Talks to Buy Clutch Security for $500 Million Nov 5 OpenAI Cyber Model Finds 948 Linux Kernel Privilege Escalation Flaws Nov 4 Google Cloud Adds Security Controls for AI AgentsCybersecurity AI Weekly
Weekly newsletter about AI in Cybersecurity.
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
Cursor Removes Malicious Claude Code Extension, Warns Up to 5,000 Users
Claude Security Adds Continuous Repository Scanning
Anthropic Adds Claude Self Assessment to Detect Misuse
CrowdStrike finds four groups using Claude Code in cyberattacks
Anthropic Model Builds Exploits for Chrome, Safari, Windows and Linux
Daily AI Brief: the AI news that matters, in your inbox.