LiteLLM compromised: 92M-downloads/month Python package shipped credential-stealing malware in v1.107.0
KyeGomezB · x · 2026-10-22
Per a Socket Security report, LiteLLM — a Python package for connecting to AI model providers with 92M+ monthly downloads — has been compromised. Version 1.107.0 ships credential-stealing malware through PyPI wheels and Docker images, targeting cloud credentials, developer secrets, and AI tooling.
The poster (Swarms' Kye Gomez) uses the incident to promote RouteHub, an alternative router built on the official OpenAI SDK claiming 20+ providers, 190x faster imports (5.5ms), and 0.004ms per-call overhead vs LiteLLM's 0.74ms — treat the promo with skepticism, but the supply-chain attack itself is confirmed and teams running LiteLLM should check versions and rotate credentials immediately.
More from Infra
- Agentic era needs its own infrastructure stack: security, privacy and governance — atShruti · 2026-10-22
- IBM Brings Spyre Accelerator to PyTorch Compiler and vLLM, Outlined at PyTorchCon 2026 — PyTorch · 2026-10-22
- Nscale listed 10,000MW of 'potential' capacity in its S-1 — built under 1% — SumitGup · 2026-10-22
- Six months later, the best AI costs 20× less — Tgoc · 2026-10-22
- Single RTX 5080 runs Qwen3.8-Flash-Next at 150 tok/s decode, 4.4K tok/s prompt — yehyakar · 2026-10-22
- Google and Meta open-source TorchTPU: native PyTorch backend for TPUs — PyTorch · 2026-10-22