Meta’s Muse assistant faces a zero-day security vulnerability
Meta’s Muse AI assistant has a zero-day vulnerability that can allow locally running applications and commands entered in the terminal to take complete control of the agent. The issue challenges security assurances from Meta founder and CEO Mark Zuckerberg, who has described Muse as designed for privacy and security. A simple ClickFix attack is reportedly one possible route to hijacking the assistant.
Meta introduced Muse a few weeks ago as a macOS application that can book appointments, complete forms, manage customer-service tasks, make purchases, generate images, create documents and work with external apps. It can access services including WhatsApp, email, calendars and social-media accounts, after users authenticate it and grant operating-system permissions.
Those permissions may include writing files, using the microphone and camera, and monitoring location and calendars. Muse can also create tools when a required function is unavailable. Apple’s built-in protections are intended to restrict installed applications and terminal commands from reaching such resources, but the vulnerability undermines those safeguards for Muse. Amazon began blocking Muse from its site on Sunday.
Written by Sakhanda Wire AI from reporting by Ars Technica. Facts, quotes and full context are in the original article below.