Exploit / PoCmedium
New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands
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
Ask an AI agent to summarize the reviews on a product page, and a single planted review can make it click "Buy Now" instead. Ask a coding assistant to apply a maintainer's fix from a GitHub thread, and a fake comment can make it run a stranger's command on your computer. Neither trick hijacks the agent's task.
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.