2026年7月13日 9:49 ET 发布 · 更新于 4 个月前 · 1 个来源
New MemGhost Attack Plants Persistent False Memories in AI Agents Through One Email
The Hacker News
·
原始报道
Give an AI assistant a memory and access to your inbox, and you hand an attacker a way to rewrite what it thinks it knows about you. A single email can trick that agent into saving a false "fact" about the user, hide the change, and quietly steer its answers in later sessions. When it works, the person reads an ordinary-looking reply and never learns their assistant was tampered with. The
原文