<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Cybersecurity on LegalRealist AI</title><link>https://legalrealist.ai/tags/cybersecurity/</link><description>Recent content in Cybersecurity on LegalRealist AI</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>hi@legalrealist.ai (LegalRealist AI)</managingEditor><webMaster>hi@legalrealist.ai (LegalRealist AI)</webMaster><copyright>© 2026 LegalRealist AI</copyright><lastBuildDate>Sat, 23 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://legalrealist.ai/tags/cybersecurity/index.xml" rel="self" type="application/rss+xml"/><item><title>When Documents Are the Attack Surface</title><link>https://legalrealist.ai/posts/36-when-ai-is-the-attack-surface/</link><pubDate>Sat, 23 May 2026 00:00:00 +0000</pubDate><author>hi@legalrealist.ai (LegalRealist AI)</author><guid>https://legalrealist.ai/posts/36-when-ai-is-the-attack-surface/</guid><description>The attack surface isn&amp;rsquo;t AI — it&amp;rsquo;s the documents AI processes. Prompt injection in discovery, adversarial inputs delivered through Rule 34 productions, and the cybersecurity gaps firms create by piping untrusted content through LLM pipelines.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://legalrealist.ai/posts/36-when-ai-is-the-attack-surface/feature.png"/></item></channel></rss>