Data breachcritical
New MemGhost Attack Plants Persistent False Memories in AI Agents Through One Email
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2025-32711 | Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network | 7.5 | 7% |
From the original article
7 min read at thehackernews.com
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.
By @TheHackersNews · thehackernews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.