#LiteLLM
Malicious LiteLLM 1.107.0 Package Steals Credentials and Opens RAT Channel
LiteLLM 1.107.0 was compromised on PyPI and in container images, delivering a credential stealer plus a remote-code loading mechanism. Anyone who installed the release should isolate affected systems,...
AI Gateways Under Fire: Attackers Chain LiteLLM and MCP Flaws for Remote Code Execution
A 90-day honeypot study shows attackers systematically probing AI proxies, MCP servers, and agent frameworks like LangChain and Langflow, chaining authentication bypass and command-injection bugs into remote code...