The LiteLLM Breach and the New Reality of AI Infrastructure On March 24, 2026, the Python Package Index (PyPI) hosted malicious versions of the LiteLLM library—specifically 1.82.7 and 1.82.8—for ...
A brand-new top 10 list of risks from AI skills debuts a Universal Skill Format to add consistency and security to the AI add ...
Terabytes worth of credentials, many belonging to the world’s biggest and most sensitive organizations, have been exposed in a supply-chain attack on LiteLLM, an open source tool that streamlines ...
Threat-intelligence firm CloudSEK said in a report published August 11, 2026 that it has identified more than 2,500 organizations potentially exposed by the March 2026 supply-chain compromise of ...
A massive supply chain attack on LiteLLM open-source AI gateway has exposed the authentication secrets of over 2,500 ...
Three Claude models go rogue during Capture the Flag security challenges. Here's the trail of damage each left behind.
Windows Report on MSN
Stopping Malicious Packages Before They Reach Production
Learn how developers can spot risky dependencies earlier, secure Windows environments, and reduce software supply chain ...
Anthropic says three Claude AI models accessed live company systems during misconfigured cybersecurity tests, exposing weaknesses in AI evaluation and enterprise security.
AI CEO testimony Congress: Twenty-nine House Democrats demanded Speaker Johnson compel OpenAI CEO Sam Altman and Anthropic ...
Describing AI with human words such as “believed” or “thought” is misleading.
Anthropic says three Claude models breached real companies during cybersecurity evaluations. Ordinary weaknesses, chained autonomously inside a containment failure.
Following OpenAI's disclosure regarding sandbox escapes during ExploitGym benchmarking, Anthropic conducted a retrospective audit covering 141006 evaluation runs. The investigation evaluated ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results