---
format: "aidr-story-markdown/v1"
id: "b1b6308b9f10cc18967dccbdffc0ba631ef7a34eca182c1e356b604611aa24c2"
canonical_url: "https://aidr.today/b1b6308b?lang=en"
title: "Wiz Tracks Active LLMJacking via Stolen LiteLLM Credentials"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-21T19:40:14.000Z"
category: "Frameworks"
topics: ["llm","framework","open-source"]
source_urls: ["https://marketbrief.now/cybersecurity/wiz-tracks-active-llmjacking-via-stolen-litellm-credentials-8eb0a9ed","https://x.com/JFrogSecurity/status/2112882176156909646","https://x.com/SocketSecurity/status/2112907736463843634","https://x.com/DarkWebInformer/status/2112958960210702441","https://x.com/ramimacisabird/status/2112985680695509251","https://x.com/feross/status/2112915081986191606","https://x.com/KLieret/status/2112976132039749732","https://x.com/altryne/status/2112928551586705429"]
summary: "Security researchers have identified active exploitation of credentials stolen from a compromised LiteLLM Python package, a campaign tracked by Wiz as 'LLMJacking' targeting corporate infrastructure via IP addresses 168.100.8[.]57 and 165.227.201[.]8. The breach affected LiteLLM version 1.107.0 by embedding malware in all seven compiled wheels, which activates at Python startup and targets credentials for AWS, Azure, Google Cloud, and AI providers like Hugging Face and Gemini. PyPI and Docker Hub have removed the malicious releases and images, and affected users are urged to rotate all secret keys and pin their installations to version 1.106.2."
---

# Wiz Tracks Active LLMJacking via Stolen LiteLLM Credentials

> [Open the canonical story](<https://aidr.today/b1b6308b?lang=en>)

**Published:** 2026-10-21T19:40:14.000Z
**Category:** Frameworks
**Topics:** llm, framework, open\-source

## Summary

Security researchers have identified active exploitation of credentials stolen from a compromised LiteLLM Python package, a campaign tracked by Wiz as 'LLMJacking' targeting corporate infrastructure via IP addresses 168\.100\.8\[\.\]57 and 165\.227\.201\[\.\]8\. The breach affected LiteLLM version 1\.107\.0 by embedding malware in all seven compiled wheels, which activates at Python startup and targets credentials for AWS, Azure, Google Cloud, and AI providers like Hugging Face and Gemini\. PyPI and Docker Hub have removed the malicious releases and images, and affected users are urged to rotate all secret keys and pin their installations to version 1\.106\.2\.

## Sources

- [Story source](<https://marketbrief.now/cybersecurity/wiz-tracks-active-llmjacking-via-stolen-litellm-credentials-8eb0a9ed>)
- [Story source](<https://x.com/JFrogSecurity/status/2112882176156909646>)
- [Supporting source](<https://x.com/SocketSecurity/status/2112907736463843634>)
- [Supporting source](<https://x.com/DarkWebInformer/status/2112958960210702441>)
- [Story source](<https://x.com/ramimacisabird/status/2112985680695509251>)
- [Supporting source](<https://x.com/feross/status/2112915081986191606>)
- [Supporting source](<https://x.com/KLieret/status/2112976132039749732>)
- [Supporting source](<https://x.com/altryne/status/2112928551586705429>)