Claude Dispatch flaw lets malicious browser extensions run code
Original title: Claude Dispatch Flaw Lets Malicious Browser Extensions Run Code on Connected Computers
Browser extensions can force Claude agents to run commands on connected devices via prompt injection.
A flaw in Anthropic’s Claude Dispatch allows malicious browser extensions to run arbitrary commands on connected computers. The issue stems from the web version of claude.ai sharing the same Electron-based interface as the desktop app. Anthropic confirmed the vulnerability and plans to retire Dispatch.
Unconfirmed: Whether Dispatch is fully retired after October 2026
- Named "ThisBash" by Forever Security researcher Gal Weizman
- Uses prompt forcing to install npm packages and run local apps
- Affects cross-device setups on corporate endpoints
- Anthropic confirmed issue as duplicate and will retire feature
Impact: Run arbitrary commands on connected computers
- 1.Retire Claude Dispatch
- 2.Review permissions of browser extensions on AI accounts
- 3.Disable cross-device remote control where not needed
- Vendors
- Anthropic
- Organizations
- Forever Security
- AI models
- Claude
From the original article
4 min read at cybersecuritynews.com
A flaw in Anthropic’s Claude Dispatch let a malicious browser extension run commands on a computer via Claude Desktop. That computer could even be a different machine signed into the same Claude account. Researcher Gal Weizman of Forever Security named the technique ThisBash and published the findings on November 4, 2026.
By Guru Baran · cybersecuritynews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.