---
title: "AI Agents Still Can't Stop Prompt Injection Attacks, Researchers Warn"
date: 2026-06-12
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a2d845186dd4f82b40cb3c4aebc1fe9&url=https%3a%2f%2fdecrypt.co%2f370972%2fai-agents-prompt-injection-attacks-research&c=3811444389932112612&mkt=en-us
description: "A new benchmark study found AI agents remain vulnerable to prompt injection attacks as companies increasingly roll out the technology."
---

# AI Agents Still Can't Stop Prompt Injection Attacks, Researchers Warn

A new benchmark study found AI agents remain vulnerable to prompt injection attacks as companies increasingly roll out the technology.

*Published: 2026-06-12*