CVE-2026-42208 exploited within 36 hours of disclosure, exposing LiteLLM credentials, risking cloud account compromise.

A critical pre-authentication SQL injection vulnerability in BerriAI’s LiteLLM Python package came under active exploitation ...

People hacking branded AI bots can result in significant reputational, financial, and legal consequences. There appears to be ...

An attacker pushed a malicious version of the popular elementary-data package Python Package Index (PyPI) to steal sensitive ...

CVE-2026-5760 (CVSS 9.8) exposes SGLang via /v1/rerank endpoint, enabling RCE through malicious GGUF models, risking server ...

Anthropic fixed a significant vulnerability in Claude Code's handling of memories, but experts caution that memory files will ...

A design flaw – or expected behavior based on a bad design choice, depending on who is telling the story – baked into ...

Learn prompt engineering with this practical cheat sheet that covers frameworks, techniques, and tips for producing more ...

A widely used open-source PyPI package, elementary-data, was compromised in a targeted attack that inserted infostealer malware via a GitHub Actions vulnerability. The malicious update, version 0.23.3 ...

Already, BAND's early users — and enterprises more broadly — are mixing and matching AI agents powered by models from various ...

Forbes contributors publish independent expert analyses and insights. I cover emerging technologies with a focus on ...