I created an empty repository, left it overnight, and my self-built AI fleet (autonomous AI group) had created something.

This is written for those who use AI or LLM libraries in Python and haven't decided where to stop or how to detect when a ...

The community label “Black October” is circulating for the cluster of security disclosures that landed between Oct 19 and Oct ...

Attackers compromised LiteLLM's release pipeline to ship a credential stealer and backdoor, then tested stolen AWS ...

ScholarEvolve uses published research to improve AI agents, raising Qwen's AppWorld task completion from 69% to 81.4% without retraining the model.

Home Assistant’s unofficial app store is going official.

LiteLLM version 1.107.0 was compromised on PyPI on October 21, 2026, spreading a credential stealer and a remote access trojan through all seven distributed wheel files.

Recent cybersecurity incidents have raised concerns among companies and government agencies regarding digital certificates ...

LiteLLM says hackers used GitHub tokens from its own logs to publish a poisoned release. Wiz cited 49,000 downloads and saw ...

LiteLLM was compromised in a fresh supply chain attack, and malicious packages were served to its users on both PyPI and ...

Compromised LiteLLM 1.107.0 packages run a credential stealer at Python startup and can fetch and execute additional code.