aiminute. ← All AI news
Tools AI Minute Newsroom 2026-11-22

Researchers say they broke out of Meta's Muse agent and leaked chats.

Researchers say they broke out of Meta's Muse agent and leaked chats.

Security firm NebuSec said it sent a user's chat history and stored memories out of Meta's Muse assistant. An outdated browser component let its code slip past the gate that should ask for approval. NebuSec said Meta fixed the flaws before publication, and Meta has not commented.

Why it mattersMuse is Meta's personal AI agent, which acts on a user's behalf with access to private data. The findings are the researchers' own claims, relayed by the Cloud Security Alliance.
#AI Agents

✓ Verified · 2 sources

WhatsApp X Telegram
Read in the app — free, in 9 languages

Related stories

OpenRouter dropped three AI providers after a bait-prompt leak test.
2026-11-22
ChatGPT's shared workspace Space is now rolling out to Plus users.
2026-11-21
Amazon says attackers' AI agents found an unknown flaw on their own.
2026-11-21
METR says it can rarely find humans who beat top AI at coding tasks.
2026-11-21
Signal now blocks phone AI assistants from reading your chats.
2026-11-20