The release of the OWASP Top 10 for LLM Applications 2025 provides a comprehensive overview of the evolving security challenges in the world of Large Language Models (LLMs). With advancements in AI, the adoption of LLMs like GPT-4, LaMDA, and PaLM has grown, but so have the risks. The new 2025 list builds upon the foundational threats outlined in previous years, reflecting the changing landscape of LLM security.

A new and growing threat has emerged, targeting vulnerable PHP servers with a sophisticated cryptocurrency mining attack. This exploit takes advantage of misconfigured or unpatched PHP servers, allowing malicious actors to gain unauthorized access and deploy mining malware. The campaign focuses on exploiting vulnerabilities in PHP, particularly CVE-2024-4577, which has already been linked to several exploit attempts and continues to affect systems worldwide.