Discover the AI Agent Safety Directory that evaluates AI agents before deployment with trusted safety ratings, risk insights, and performance benchmarks.

Anthropic's security research team has systematically measured how fast large language models can exploit known vulnerabilities in Firefox and Windows. The results blow up long-standing assumptions ...

No sooner did Anthropic file for its initial public offering of stock this week than it then put out a missive suggesting that AI model makers need to slow down to let us catch our breath — or else AI ...

A npm supply chain attack named Miasma compromised 32 official packages under Red Hat's @redhat-cloud-services namespace on June 1, 2026, injecting a self-propagating credential-stealing worm that ...

A widely active phishing-as-a-service (PhaaS) operation known as FlowerStorm has begun using a browser-based virtual machine to conceal credential theft code, marking what researchers say is an ...

A malicious Hugging Face repository managed to take a spot in the platform's trending list by impersonating OpenAI's Privacy Filter open-weight model to deliver a ...

Picture this scenario: An Anthropic Skill scanner runs a full analysis of a Skill pulled from ClawHub or skills.sh. Its markdown instructions are clean, and no prompt injection is detected. No shell ...

Lets geek out. The HackerNoon library is now ranked by reading time created. Start learning by what others read most. Lets geek out. The HackerNoon library is now ranked by reading time created. Start ...

A rogue AI agent at Meta passed every identity check and still exposed sensitive data to unauthorized employees in March. Two weeks later, Mercor, a $10 billion AI startup, confirmed a supply-chain ...

Can Elon Musk pull off the mother of all IPOs? This week his SpaceX reportedly filed confidentially for a $75 billion initial public offering that could value it at $1.75T. It would be the largest IPO ...

Digital crime is now so costly that, were it an economy, it would rank behind only the GDPs of the U.S. and China. Increasingly, we depend on data integrity for our very lives, and some of the biggest ...

Aqua Security revealed on March 21 that attackers hijacked 75 of 76 GitHub Actions tags for its Trivy vulnerability scanner, distributing credential-stealing malware through the widely used security ...