Filtered by tag: ai tools × Clear
LiteLLM Compromised – Hackers Injected an Infostealer and RAT in the Latest 1.107.0 PyPI Release
Matched: health
LiteLLM version 1.107.0 was compromised on PyPI on October 21, 2026, with all seven wheel files containing a credential stealer and remote access trojan that also spread to Docker images. The malware uses Python startup hooks to run automatically without LiteLLM being directly invoked, targeting SSH keys, cloud credentials, browser passwords, and AI tool tokens. Data is sent to an attacker-controlled domain mimicking LiteLLM infrastructure. PyPI removed the release, but stolen credentials remain at risk. Version 1.106.2 is considered safe.