SecurityTechRadarabout 2 hours ago
Meta Muse zero-day lets attackers hijack AI tokens
6 min read
Security researcher Patrick Wardle found a zero-day in Meta's new Muse AI assistant, dubbed not-a-mused. Exploiting it requires local compromise, voice dictation and app integrations; attackers redirect dictation to steal authentication tokens and exfiltrate data from connected apps like WhatsApp and email. Meta has been informed but has not patched or commented.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMeta
