---
title: "The Real AI Security Risk Isn't Data Leakage. It's What Your Agents Can Do"
date: 2026-05-11
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a03b269105e433fa0c3f6a716c29a0d&url=https%3a%2f%2fwww.forbes.com%2fsites%2fguneyyildiz%2f2026%2f05%2f11%2fthe-real-ai-security-risk-isnt-data-leakage-its-what-your-agents-can-do%2f&c=16584735691938780269&mkt=en-us
description: "Agentic AI has moved the threat boundary inside the enterprise. Mindgard's Aaron Portnoy explains why authority, not access, is now the primary vulnerability."
---

# The Real AI Security Risk Isn't Data Leakage. It's What Your Agents Can Do

Agentic AI has moved the threat boundary inside the enterprise. Mindgard's Aaron Portnoy explains why authority, not access, is now the primary vulnerability.

*Published: 2026-05-11*