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 ...
A poisoned npm package infected 140+ projects with a hidden payload. This report highlights how to detect, hunt, and defend ...
Researchers found 15 malicious JetBrains plugins posing as AI coding tools that exfiltrate OpenAI, DeepSeek, and SiliconFlow ...