Tools
157d agoLiteLLM Proxy Breached, Malware Spreads Globally
LiteLLM, a widely used open‑source proxy for AI APIs, has been compromised by malware that steals credentials and propagates through Kubernetes clusters worldwide. The attack exposes a new class of threats aimed at AI agents, raising alarms for global AI infrastructure security.
The Signal
NVIDIA officials warn that such breaches could cripple cloud‑based AI services.