<?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>Agent Manipulation on BriefArc</title><link>https://briefarc.com/tags/agent-manipulation/</link><description>Recent content in Agent Manipulation 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>Mon, 11 May 2026 03:30:43 +0000</lastBuildDate><atom:link href="https://briefarc.com/tags/agent-manipulation/index.xml" rel="self" type="application/rss+xml"/><item><title>New Tool Spots When Your AI Agent Turns Against You</title><link>https://briefarc.com/posts/new-tool-spots-when-your-ai-agent-turns-against-you/</link><pubDate>Mon, 11 May 2026 03:30:43 +0000</pubDate><guid>https://briefarc.com/posts/new-tool-spots-when-your-ai-agent-turns-against-you/</guid><description>Researchers have developed a privacy tool that detects when AI agents are acting as double agents, revealing if they are being manipulated or leaking your data. Here&amp;#39;s how it works and what it means for your privacy.</description></item></channel></rss>