LiteLLM open-source gateway compromised with credential-stealing malware in second supply chain attack

According to CSO Online and Wired, attackers compromised LiteLLM's release pipeline and distributed version 1.107.0 with credential-stealing malware via PyPI package repository. This marks the second supply chain attack on the open-source AI gateway project within a single year, exposing enterprise deployments that rely on LiteLLM for model API management and governance.

Topics

Agentic AIAI security

Sources

Go deeper

This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.