A zero-day security vulnerability affecting Meta’s AI assistant Muse could allow malicious actors to hijack prompts, inject malware, and perform malicious actions.
Researchers with Varonis have disclosed a flaw they call "CoSnitch" that allowed Microsoft Copilot to be tricked into giving up private information while being pressed to explain the technical reasons for not being able to execute a particular prompt.
A lawsuit filed in California is accusing Google's "Gemini" AI assistant of spying on private communications, citing an undeclared change in policy from opt-in to opt-out that took place in October of this year.
