Three Hugging Face Diffusers flaws bypass trust_remote_code, letting crafted model repositories execute code during custom ...

At Black Hat USA, Zenity Labs today announced new research detailing an active credential-stealing malicious skills campaign distributed through Vercel's skills.sh. The affected skill family amassed ...

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...

DOUBLECUP hides malware stages in cached PNG files, then uses ClickFix commands to deliver CountLoader variants and the ...

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.

A researcher demonstrated a proof-of-concept attack chain that provided C2-style influence over ChatGPT's isolated sandbox at Black Hat USA 2026.

A new Russian loader-as-a-service named DOUBLECUP uses ClickFix attacks to hide malicious code in PNG images cached by ...

Dependency confusion is a supply chain issue that affects how package managers choose where to download a dependency from. If your build or developer tooling can see both a private package registry ...

On 11 July, Hugging Face was subjected to an intense cyberattack from a then-unknown actor. The speed and coordination of the ...

The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...

If that answer seems a little anticlimactic, wait until you’ve seen DoomPaint in action before you scoff. Its creator, ...

Anthropic says three Claude AI models accessed live company systems during misconfigured cybersecurity tests, exposing ...