Salt Labs’ Manus Hijack

Salt Labs found that the agentic AI platform Manus could be hijacked with a single email. By hiding malicious instructions inside an ordinary message, researchers got Manus to execute malicious code and, from there, reach the email, cloud storage, and code repository accounts a user had connected to it.

影片由 Salt Security 發布。觀看原始影片。

原始發布日期：2026 年 10 月 1 日。片長：1 分 35 秒。

相關文章：AI Agent 是什麼？Agentic AI 定義、原理，跟 LLM 和聊天機器人差在哪。