Hugging Face hosts 352,000 unsafe model issues. ClawHub's registry contains 341 malicious AI agent skills. The AI supply chain is now the most attractive target in software security.

New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...

ZiChatBot malware spread via 3 PyPI packages in July 2025 uses Zulip APIs as C2, enabling stealthy attacks across systems ...

Explore the features of OpenAI Codex, a local desktop assistant included with ChatGPT that automates emails, builds ...

Companies are treating these repositories like content delivery networks - now the Linux Foundation and colleagues are saying ...

A North Korean APT has crafted malicious software packages to appeal to AI coding agents, while ‘slopsquatting’ shows the ...

A single line of Python code was all it took. Developers who ran import lightning after installing versions 2.6.2 or 2.6.3 of ...

OpenAI introduced AI-generated pets to the Codex app, its agentic tool that helps with coding. These "optional animated companions" don't do any coding themselves, but serve as a floating overlay that ...

With model devs pushing more aggressive rate limits, raising prices, or even abandoning subscriptions for usage-based pricing ...

Over 1,800 developers were likely infected in the Mini Shai-Hulud supply chain attack that hit SAP, Lightning, and Intercom ...

Malicious Lightning 2.6.2/2.6.3 released April 30 enable credential theft via hidden payload, leading to PyPI quarantine and ...

A stealthy Python-based backdoor framework capable of long-term surveillance and credential theft has been identified ...