A Single Malicious Webpage Let Researchers Hijack Meta Muse and Access Private Chats
Researchers demonstrate a malicious webpage can hijack Meta Muse AI and access private chats.
Researchers demonstrated that a malicious webpage could extract private conversations and stored memories from Meta's AI agent, Muse, without user approval. The attack could also access credentials for connected accounts and take full control of the user's cloud machine by chaining a browser flaw with a Linux kernel flaw. The security firm NebuSec reported the findings, and Muse's team has since fixed all described weaknesses.
AI summary of the linked source. Not reviewed by an editor. How this works
Run Meta?
Get an email when a new story names Meta, usually within the hour.
Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy
The lesson from this incident
Full lessonResearchers at NebuSec discovered that simply visiting a malicious webpage was enough to chain a browser vulnerability with a Linux kernel flaw, allowing an attacker to extract private AI conversations, stored memories, and cloud credentials from Meta's Muse agent without any user consent. The attack succeeded because two distinct unpatched vulnerabilities existed simultaneously and could be exploited in sequence, dramatically amplifying the impact of each individual flaw. This highlights how AI agents with broad system access create a high-value, high-risk attack surface where unpatched components can lead to full machine compromise. Organizations deploying AI agents must treat both the underlying OS and browser runtime as critical attack surfaces requiring timely patching and strict privilege boundaries.
What helps against this
How we list vendors- Vulnerability scanning and prioritisation
You know which systems are vulnerable, and which ones to fix first.
- Endpoint detection and response (EDR and XDR)
Malware and hands-on-keyboard attackers on laptops and servers get spotted and stopped.
- AI application security
Prompt injection, data leaks through AI tools and unapproved AI use get caught.