<?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>Agentic security on sigprobe</title><link>https://personal-blog-1jz.pages.dev/research/agentic-security/</link><description>Recent content in Agentic security on sigprobe</description><image><title>sigprobe</title><url>https://personal-blog-1jz.pages.dev/og.png</url><link>https://personal-blog-1jz.pages.dev/og.png</link></image><generator>Hugo</generator><language>en-us</language><copyright>2026 Matt</copyright><lastBuildDate>Tue, 03 Nov 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://personal-blog-1jz.pages.dev/research/agentic-security/index.xml" rel="self" type="application/rss+xml"/><item><title>Getting more out of a coding agent for vulnerability research: context, tools and a review loop</title><link>https://personal-blog-1jz.pages.dev/writeups/placeholder-agent-vulnerability-research/</link><pubDate>Tue, 03 Nov 2026 09:00:00 +0000</pubDate><guid>https://personal-blog-1jz.pages.dev/writeups/placeholder-agent-vulnerability-research/</guid><description>A coding agent finds more real bugs when it is given the right context and a way to check its own work. What I hand it, which tools I wire in, and the review loop that keeps false positives from eating my day.</description></item><item><title>Where agents fall down at reverse engineering: triaging a firmware image with an LLM</title><link>https://personal-blog-1jz.pages.dev/writeups/placeholder-agent-firmware-triage/</link><pubDate>Tue, 29 Sep 2026 09:00:00 +0000</pubDate><guid>https://personal-blog-1jz.pages.dev/writeups/placeholder-agent-firmware-triage/</guid><description>A field report from letting an agent loose on an unpacked firmware image. It was excellent at the boring parts, confidently wrong about the interesting ones, and the difference came down to what it could actually run.</description></item></channel></rss>