<?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>Kali on Angus Dawson — Homelab &amp; CTFs</title><link>https://basil9099.github.io/tags/kali/</link><description>Recent content in Kali on Angus Dawson — Homelab &amp; CTFs</description><image><title>Angus Dawson — Homelab &amp; CTFs</title><url>https://basil9099.github.io/images/og-default.png</url><link>https://basil9099.github.io/images/og-default.png</link></image><generator>Hugo -- 0.165.0</generator><language>en-us</language><lastBuildDate>Tue, 04 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://basil9099.github.io/tags/kali/index.xml" rel="self" type="application/rss+xml"/><item><title>Building a Local-AI Bug Bounty Lab — and Where I Learned Not to Trust It</title><link>https://basil9099.github.io/homelab/local-ai-bug-bounty-lab/</link><pubDate>Tue, 04 Aug 2026 00:00:00 +0000</pubDate><guid>https://basil9099.github.io/homelab/local-ai-bug-bounty-lab/</guid><description>I connected an AI-driven recon tool to a self-hosted LLM running on my own GPU, drove it from a Kali attack VM, and pointed it at a ClassicPress target on a segment I control. Cross-host inference, a VRAM wall, a clean run against the wrong target, and the lesson I keep relearning: a local model is a lead generator, not an oracle.</description></item></channel></rss>