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

PCPJack steals credentials via 6 Python modules exploiting 5 CVEs, enabling cloud spread and fraud-driven attacks.

We tested our own computers to see if the model was present.

You can nix Chrome's 4GB local AI model in just a few clicks, but you'll lose some functionality in the process.

The terminal is fine. But if you actually want to live in your Hermes agent, here are the four best GUIs the community has ...

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

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

ScarCruft spreads BirdCall via sqgame.net since late 2024, targeting Android users, enabling surveillance and data theft.

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.

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

ESET researchers have investigated an ongoing attack by the ScarCruft APT group that targets the Yanbian region via ...