CriticalAPT
Claude Dispatch Flaw Lets Malicious Browser Extensions Run Code on Connected Computers
Cyber Security News·Source published ·1 min read
What happened?
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. Anthropic plans to retire Dispatch, but the design behind it still lives in other Claude features. Dispatch lets a person send a task from a phone to Claude Desktop, an AI agent that can work with local files, apps, and commands.
Key details
- A flaw in Claude Dispatch allowed malicious browser extensions to execute commands on connected computers via Claude Desktop.
- The vulnerability, named ThisBash, was discovered by Gal Weizman of Forever Security and published on November 4, 2026.
- Claude Desktop is an Electron app sharing the same web interface and API as claude.ai, with Dispatch accessible via copied URLs.
- Similar risks exist in Claude Code Remote Control and Cowork sessions, where web-driven local agents can be steered by extensions.
Affected
- Claude Dispatch feature in limited beta, closed to new users.
- Claude Desktop Electron application.
- Claude Code Remote Control and Cowork sessions.
Fixes and mitigations
- Turn off cross-device remote control where not needed and review device pairing and removal.
What to look for
- Tiny 200x200 pixel background window opening Dispatch.
- Odd package installs, config changes, and credential access linked to agent activity.
Summarised by SecOraLens from Cyber Security News. Always read the original source before acting. How SecOraLens verifies advisories.