TeamPCP’s Mini Shai-Hulud campaign used hijacked GitHub OIDC tokens to spread a credential-stealing worm through TanStack npm ...
Fake OpenAI Privacy Filter hit #1 on Hugging Face with 244,000 downloads, spreading infostealer malware to Windows users.
TanStack had 2FA, OIDC publishing, and Sigstore provenance on every release. The Mini Shai-Hulud worm published 84 malicious ...
Researchers demonstrate how attackers can weaponize trusted repositories to hijack AI coding assistants and compromise ...
A malicious Hugging Face repository that reached the platform's trending list impersonated OpenAI's "Privacy Filter" project ...
A fake repo impersonating the OpenAI Privacy Filter model racked up 244,000 downloads in under 18 hours before Hugging Face ...
The repository reached the #1 trending position on Hugging Face within 18 hours, highlighting how public AI repositories are ...
Today's applications require monitoring, logging, configuration, etc. Each of these concerns can be implemented as a ...
A 6MB editor quietly replacing tools that cost ten times more.
Google says attackers are using AI for zero-day research, malware development, reconnaissance, and access to premium AI tools ...
Google's GTIG identified the first zero-day exploit developed with AI and stopped a mass exploitation event. The report documents state actors using AI for vulnerability research and autonomous ...
Android apps that do their jobs without AI getting in the way ...