museIMAGE

Meta patches Muse vulnerability that let attackers hijack the AI agent

A security researcher found a flaw in Meta's Muse AI app that let attackers control the AI agent, take photos and write malicious files without alerting the user; Meta has patched it.

Interesting AF

@interesting_aIlArchived 2026.09.27Originally posted 2026.09.27

Meta patches Muse vulnerability that let attackers hijack the AI agent (image 1 of 2)

Meta patches Muse vulnerability that let attackers hijack the AI agent (image 2 of 2)

Interesting AF @interesting_aIlOriginally posted 2026.09.27

Open original on X

Meta patches a vulnerability in its Muse AI app that allowed attackers to take control of the AI agent, take photos and write malicious files without alerting the user A security researcher discovered the flaw and warned Meta wasn't thinking about security from the start

x.com/interesting_ail/status/2103937653741613468Archived 2026.09.27 10:09