‘Zoomsday’ hack uncovered using fewer than 20 AI prompts

Zoom patched a major security flaw that could let an attacker hijack a participant's device during a meeting. Researchers at A Security discovered the issue by issuing fewer than 20 prompts to publicly available AI models, exploiting Zoom's annotation feature. The vulnerability allowed an attacker to join or host a meeting and take control of the victim's device.

Summary written by Kernelia from the original article by The Verge — AI. The story and its rights belong to its author.