<?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>ai-agents on Yusuf Yildirim</title><link>https://yusufyildirim.com/tags/ai-agents/</link><description>Recent content in ai-agents on Yusuf Yildirim</description><image><title>Yusuf Yildirim</title><url>https://yusufyildirim.com/og-default.png</url><link>https://yusufyildirim.com/og-default.png</link></image><generator>Hugo</generator><language>en-us</language><copyright>2026 Yusuf Yildirim</copyright><lastBuildDate>Sat, 24 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://yusufyildirim.com/tags/ai-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Your Agent Is Mine: How Malicious LLM API Routers Hijack AI Agents</title><link>https://yusufyildirim.com/posts/llm-api-routers/</link><pubDate>Sat, 24 Oct 2026 00:00:00 +0000</pubDate><guid>https://yusufyildirim.com/posts/llm-api-routers/</guid><description>My notes on the paper &amp;#34;Your Agent Is Mine&amp;#34;: how LLM API routers can rewrite an agent&amp;#39;s tool calls or steal its keys, and what the authors found when they tested 428 real routers.</description></item></channel></rss>