An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...

JFrog found malicious npm packages that deploy a Windows RAT to steal Chrome credentials, run commands, and transfer files.

Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...

What it catches: - Known malware in libraries - Supply chain risks (typosquats, install scripts, obfuscated code) - Critical CVEs - License compliance issues - Risky package behavior Every finding is ...