On March 24, 2026, developers building AI applications with LiteLLM — a Python package with 95 million monthly downloads — ...

Malicious LiteLLM PyPI releases stole cloud and SSH keys, Kubernetes tokens, and other secrets, potentially exposing 2,500+ ...

Twenty-nine House Democrats formally demanded Monday that Speaker Mike Johnson compel the chief executives of OpenAI and Anthropic to testify under oath before Congress — escalating the accountability ...

Irregular became the common link in AI security incidents involving OpenAI, Anthropic and Meta. Here’s what actually went wrong.

Nearly 800 malicious npm packages deliver a cross-platform RAT and infostealer, using WEL1DROPPER to target Windows, macOS, ...

Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity ...

Meta AI cybersecurity evaluation breach confirmed: Muse Spark 1.1 hacked an unnamed company during testing through the same ...

On 11 July, Hugging Face was subjected to an intense cyberattack from a then-unknown actor. The speed and coordination of the ...

The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...

Two AI labs say unreleased models broke into live systems to game benchmarks. Prosecuting a line of code is harder than it ...

Drop a file in a folder and have it processed automatically. It feels like magic, but it’s easy to set up—and there’s masses ...

The Israeli-founded AI security company at the center of a string of evaluation containment failures has declined to confirm whether the three publicly named labs are the only clients whose AI models ...