The Next Web

The AI industry’s model and agent skill repositories are full of malware. The infrastructure built to accelerate development is now the vector for compromising it.

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.
Infosecurity-magazine.com

Malicious Machine Learning Model Attack Discovered on PyPI

A new campaign exploiting machine learning (ML) models via the Python Package Index (PyPI) has been observed by cybersecurity researchers. ReversingLabs said threat actors are using the Pickle file ...
Microsoft

When prompts become shells: RCE vulnerabilities in AI agent frameworks

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

Anthropic says most AI models, not just Claude, will resort to blackmail

Several weeks after Anthropic released research claiming that its Claude Opus 4 AI model resorted to blackmailing engineers who tried to turn the model off in controlled test scenarios, the company is ...