LiteLLM

Unsloth Studio, a new beta desktop application designed to make fine-tuning and running AI models faster, easier, and more affordable, has implemented enhanced safety protocols in response to significant security incidents.

Google Cloud AI Research, in a significant collaborative effort with leading academic institutions including UNC-Chapel Hill, Stanford University, and Washington University in St. Louis, has introduced Regularized Recursive Self-Improvement (RRSI).

Wiz Research discovered that approximately 10% of internet-facing LiteLLM servers scanned in February 2024 accepted the example administrator key, "sk-1234." This key is explicitly provided within LiteLLM's setup guide as a default credential.

The Australian Federal Police (AFP) has charged two Western Australian men, Louis Michael Gaebler, 23, and Ruben Ian Thomson, 21, with a total of 14 offenses for their alleged involvement in the cybercrime group TeamPCP.

Two malicious versions of the open-source LiteLLM Python package were discovered on the Python Package Index (PyPI) in March, remaining undetected for approximately 40 minutes before being removed. These compromised packages contained malicious code designed to steal sensitive credentials…

Obsidian Security researchers disclosed a chain of three vulnerabilities in LiteLLM, an open-source AI gateway, that allows low-privilege users to gain full administrative control and execute code on the server.

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) added a critical flaw affecting BerriAI LiteLLM to its Known Exploited Vulnerabilities (KEV) catalog on Monday, citing evidence of active exploitation. The vulnerability, identified as CVE-2026-42271 and assigned a CVSS score…