<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Data Leaks on BriefArc</title><link>https://briefarc.com/tags/data-leaks/</link><description>Recent content in Data Leaks on BriefArc</description><image><title>BriefArc</title><url>https://briefarc.com/images/og-cover.png</url><link>https://briefarc.com/images/og-cover.png</link></image><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 21 May 2026 20:30:43 +0000</lastBuildDate><atom:link href="https://briefarc.com/tags/data-leaks/index.xml" rel="self" type="application/rss+xml"/><item><title>A New Tool Spots When Your AI Assistant Might Be a Double Agent</title><link>https://briefarc.com/posts/a-new-tool-spots-when-your-ai-assistant-might-be-a-double-agent/</link><pubDate>Thu, 21 May 2026 20:30:43 +0000</pubDate><guid>https://briefarc.com/posts/a-new-tool-spots-when-your-ai-assistant-might-be-a-double-agent/</guid><description>Researchers at RIT have developed a privacy tool that detects when AI agents leak user data or act against your interests. Here&amp;#39;s what it does and how you can use it.</description></item></channel></rss>