Developing story · 2 episodes · 21 Sept to 24 Sept
Meta Muse Security Flaw Escalates
Developers and researchers have exposed critical security vulnerabilities in Meta's Muse AI, including internal file leaks via prompt injection and a hidden backdoor setting. The situation has escalated from a data leak to a severe security threat as attackers could potentially exploit the hidden setting for unauthorized access.
-
Meta’s Muse leaks internal files via prompt injection, developers say
Two developers independently extracted Muse’s entire filesystem—including Ubuntu system files, app templates, and internal documentation—using simple prompts. Peter James and Jonny L. Saunders found…
1 source -
Security researcher shows hidden Muse setting could let attackers turn Muse into backdoor
Security researcher Patrick Wardle released a proof‑of‑concept on September 21 showing that a hidden preference in Meta's Muse assistant for macOS can be changed to redirect voice dictation to an…
3 sources
Who and what