<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>AI Sec Bench</title><description>Independent benchmarks of AI security tooling. Reproducible test harnesses, real-world workloads, honest scoring across LLM scanners, prompt-injection detectors, jailbreak classifiers, and the broader AI security tooling landscape.</description><link>https://aisecbench.com/</link><language>en</language><item><title>What this site is for</title><link>https://aisecbench.com/posts/welcome/</link><guid isPermaLink="true">https://aisecbench.com/posts/welcome/</guid><description>AI Sec Bench covers cybersecurity news with an engineer&apos;s filter. Here&apos;s what we publish.</description><pubDate>Sun, 03 May 2026 00:00:00 GMT</pubDate><category>meta</category><author>AI Sec Bench Editorial</author></item></channel></rss>