---
title: "Attackers can turn AI agent guardrails into denial-of-service weapons"
date: 2026-06-15
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a3019471d9345ac95844bd1e5672bf7&url=https%3a%2f%2fwww.csoonline.com%2farticle%2f4185051%2fattackers-can-turn-ai-agent-guardrails-into-denial-of-service-weapons.html&c=5618984368315041526&mkt=en-us
description: "Researchers say a single poisoned document could slow AI agent systems by up to 148× and turn AI safety controls into an enterprise weak spot."
---

# Attackers can turn AI agent guardrails into denial-of-service weapons

Researchers say a single poisoned document could slow AI agent systems by up to 148× and turn AI safety controls into an enterprise weak spot.

*Published: 2026-06-15*