Nearly 9 in 10 security leaders struggle with identity sprawl as AI and NHIs expose governance gaps.

Speed is the most common theme among developers and appsec teams working with LLMs and agents, from trying to keep up with patterns for deploying agents to dealing with more code faster to how the latest models impact code quality and security. The OWASP GenAI Project is helping organizations keep up with the speed of those changes and engaging the...

The Model Provenance Kit allows organizations to trace model origin and similarity.

AI-found Linux flaw enables easy root access, heightening risk across cloud and shared systems.

Latest case was the second time in five weeks the Python package was exploited.

Flaw in Entra ID AI agent role enabled privilege escalation and takeover.

A new cluster of 73 extensions impersonating legitimate projects has been tied to the GlassWorm campaign.

Portswigger's list of web hacking techniques is a long-running celebration of curiosity and research from the web hacking community. James Kettle shares his thoughts on the entries from 2025 and how he expects LLMs and agents to influence what the list will look like for next year. He also shares some insights on using LLMs for his own blackbox res...