<?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/llm-security/</link><description>Infrastructure security news for people who build infrastructure.</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Thu, 30 Apr 2026 11:10:34 -0400</lastBuildDate><atom:link href="https://cybercrime.club/tags/llm-security/" rel="self" type="application/rss+xml"/><item><title>LiteLLM CVE-2026-42208: Pre-Auth SQLi in the AI Gateway, Exploited 36 Hours After Disclosure</title><link>https://cybercrime.club/posts/litellm-cve-2026-42208-preauth-sqli-ai-gateway/</link><pubDate>Thu, 30 Apr 2026 11:10:34 -0400</pubDate><guid>https://cybercrime.club/posts/litellm-cve-2026-42208-preauth-sqli-ai-gateway/</guid><description>A pre-authentication SQL injection in LiteLLM's auth path (CVSS 9.3) lets an unauthenticated attacker read and modify the proxy database — including upstream OpenAI and Anthropic API keys. First exploitation hit 36 hours after the advisory.</description><category>vulnerabilities</category></item></channel></rss>