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

Generative AI writes syntactically perfect code, but it fails nearly 44% of security tests. Discover the findings from a ...

Three Hugging Face Diffusers flaws bypass trust_remote_code, letting crafted model repositories execute code during custom ...

Google removed 3 ADK AI workflows after Pillar showed a public GitHub issue could trigger a privileged agent & reach code ...

Large language model (LLM) hallucinations are becoming a profitable side business for cybercriminals. They prod the AI models ...

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 ...

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.

At Black Hat USA, Zenity Labs today announced new research detailing an active credential-stealing malicious skills campaign distributed through Vercel's skills.sh. The affected skill family amassed ...

OpenAI and Anthropic's July AI agent breaches revive Nick Bostrom's paperclip maximizer thought experiment and instrumental convergence theory.

The March 2026 LiteLLM supply chain attack likely affected over 2,500 organizations and exposed over 430,000 CI/CD pipelines.

Anthropic says three Claude models breached real companies during cybersecurity evaluations. Ordinary weaknesses, chained ...

Typst is an easy and powerful markup-based language for creating technical documentation and books – and a compelling ...