LiteLLM offers an AI open source project used by millions that was infected by credential harvesting malware.
Delve did the security compliance on LiteLLM, an AI project hit by malware Julie Bort 5:03 PM PDT · March 25, 2026 This is one of those Silicon Valley real-life episodes that seems pulled from the HBO satire show.
This week, some really atrocious malware was discovered in an open source project developed by Y Combinator graduate LiteLLM.
LiteLLM gives developers easy access to hundreds of AI models and provides features like spend management.
It’s a breakout hit, downloaded as often as 3.4 million times per day, according to Snyk , one of the many security researchers monitoring the incident.
The project had 40K stars on GitHub and thousands of forks (those who used it as a base to alter and make it their own).
The malware was discovered, documented, and disclosed by research scientist Callum McMahon of FutureSearch, a company offering AI agents for web research.
The malware slipped in through a “dependency,” meaning other open source software that LiteLLM relied upon.