<?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>Promptinjection on The Engine Room</title><link>/en/tags/promptinjection/</link><description>Recent content in Promptinjection on The Engine Room</description><generator>Hugo -- 0.155.3</generator><language>en-us</language><lastBuildDate>Wed, 15 Oct 2025 15:00:00 +0300</lastBuildDate><atom:link href="/en/tags/promptinjection/index.xml" rel="self" type="application/rss+xml"/><item><title>Multi-Agent Pipeline for Protecting LLMs from Prompt Injection</title><link>/en/notes/multiagent_pipeline/</link><pubDate>Wed, 15 Oct 2025 15:00:00 +0300</pubDate><guid>/en/notes/multiagent_pipeline/</guid><description>An analysis of a multi-agent defense architecture that reduces prompt injection attack success by separating roles between agents.</description></item></channel></rss>