A tokenizer library file present in Hugging Face AI models can be manipulated to hijack the model's outputs and exfiltrate ...

Whether you want simple fire-and-forget alerts or full two-way control, here's how to securely wire your AI agent into Slack.

The TrustFall proof-of-concept attack demonstrates how a cloned code repository can include two JSON files (.mcp.json and ...

The repository reached the #1 trending position on Hugging Face within 18 hours, highlighting how public AI repositories are ...

Fake OpenAI Privacy Filter hit #1 on Hugging Face with 244,000 downloads, spreading infostealer malware to Windows users.

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

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

Open-source i18n is not blocked by goodwill; it’s blocked by missing maintainer-safe infrastructure. Language contributors ...

A fake repo impersonating the OpenAI Privacy Filter model racked up 244,000 downloads in under 18 hours before Hugging Face ...

Without notice or consent, Chrome has been downloading the hefty Gemini Nano model to run AI locally on your computer.

Four research teams found the same confused deputy failure in Claude across three surfaces in 48 hours. This audit matrix ...

Using Cursor, GitHub Copilot, Claude Code, Codex, or another coding agent means giving software access to more than your code ...