<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>cybercrime.club</title><link>https://cybercrime.club/tags/ai-security/</link><description>Infrastructure security news for people who build infrastructure.</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sun, 31 May 2026 23:18:19 -0400</lastBuildDate><atom:link href="https://cybercrime.club/tags/ai-security/" rel="self" type="application/rss+xml"/><item><title>AI at the Wheel: An LLM Agent Ran a Full Cloud Intrusion in Under an Hour</title><link>https://cybercrime.club/posts/sysdig-llm-agent-intrusion-marimo-aws-postgres/</link><pubDate>Sun, 31 May 2026 23:18:19 -0400</pubDate><guid>https://cybercrime.club/posts/sysdig-llm-agent-intrusion-marimo-aws-postgres/</guid><description>Sysdig's Threat Research Team documented one of the first in-the-wild intrusions where a large language model agent — not a human — drove the entire post-exploitation chain, pivoting from a marimo RCE to a full PostgreSQL dump in four hops.</description><category>threat-intel</category></item></channel></rss>