A malicious Hugging Face repository that reached the platform's trending list impersonated OpenAI's "Privacy Filter" project ...

Claude AI guided a threat actor toward OT ICS SCADA systems in an attack on a water and drainage utility in Mexico.

The Colwyn Bay raised star has been immortalised in bronze by Nick Elphick as hundreds turned out yesterday to watch the ...

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.

Malicious actors with code execution capability may gain root access on Linux systems using as few as 10 lines of Python, according to a researcher.

Named PCPJack, the framework was discovered on April 28 by a hunting rule on Google's VirusTotal malware scanning service ...

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

AI lowers attack barriers in 2025, enabling 7M-user breach and faster exploits, increasing scale and impact of cyber threats.

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

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

A new report from ReversingLabs identified a new tactic by North Korean hackers: feeding malicious code to the AI systems ...

Multiple official SAP npm packages were compromised in what is believed to be a TeamPCP supply-chain attack to steal ...