---
title: "Phantom Labs Research Shows AI Agents Are Acting Beyond Intent. BeyondTrust AI Agent Security, Now Available, Stops Them"
date: 2026-10-21
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6ad8e953338b423a807fc1126f01020d&url=https%3a%2f%2ffinance.yahoo.com%2ftechnology%2fai%2farticles%2fphantom-labs-research-shows-ai-130000978.html&c=17376127961450182643&mkt=en-us
description: "BeyondTrust Phantom Labs® observed 1.28 million shell commands requested from approximately 132,000 prompts in four weeks, averaging nearly 10 commands per prompt85% of observed coding-agent users had ..."
---

# Phantom Labs Research Shows AI Agents Are Acting Beyond Intent. BeyondTrust AI Agent Security, Now Available, Stops Them

BeyondTrust Phantom Labs® observed 1.28 million shell commands requested from approximately 132,000 prompts in four weeks, averaging nearly 10 commands per prompt85% of observed coding-agent users had ...

*Published: 2026-10-21*