<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLMjacking on HackingPassion.com : root@HackingPassion.com-[~]</title><link>https://hackingpassion.com/tags/llmjacking/</link><description>Recent content in LLMjacking on HackingPassion.com : root@HackingPassion.com-[~]</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 30 Jan 2026 14:08:05 +0100</lastBuildDate><atom:link href="https://hackingpassion.com/tags/llmjacking/index.xml" rel="self" type="application/rss+xml"/><item><title>Ollama Security Failure Exposes 175,000 AI Servers to Attackers</title><link>https://hackingpassion.com/ollama-175000-servers-exposed/</link><pubDate>Fri, 30 Jan 2026 14:08:05 +0100</pubDate><guid>https://hackingpassion.com/ollama-175000-servers-exposed/</guid><description>&lt;p>&lt;strong>175,000 AI servers wide open to the internet. 130 countries.&lt;/strong> Attackers are selling access to other people&amp;rsquo;s hardware at a 50% discount, and using it for spam, phishing, and worse. 🧐&lt;/p>
&lt;p>Running AI locally sounds like the safe option. No cloud, no third parties, everything stays on your own machine. So people install &lt;strong>Ollama&lt;/strong>, fire up a language model, and assume they&amp;rsquo;re good. Except the default settings expose the server to anyone who knows where to look.&lt;/p></description></item></channel></rss>