NewsGoogle Threat Intelligence30.10.2026

ARTEX and Friends: Enter Agentic Offensive Frameworks

Written by: Aurora Blum, David Mainor, Rohit Nambiar, Omar ElAhdan, Matthew McWhirt, Will Silverstone, Bhavesh Dhake, Chris Busse Introduction Recent intrusions in which threat actors have been observed weaponizing agentic frameworks to execute highly-automated intrusions has put a spotlight on evolving adversarial use of LLMs. In our September 2026 report , Google Threat Intelligence Group (GTIG) noted that forward leaning adversaries were beginning to transition from basic prompting to agentic workflows and LLM-enabled automation. Since this publication, GTIG and Mandiant have observed…

Other advisories

Not ratedosv:CVE-2026-115541HumHub 1.19.0 - Stored cross-site scripting in friendship confirmation
CriticalCVE-2026-92161FriendsOfFlarum Oauth: unzureichende Prüfung der Datenauthentizität
CriticalCVE-2026-92161FriendsOfFlarum OAuth: Unauthenticated account takeover via unverified email trust in Discord OAuth provider
CriticalCVE-2026-92161FriendsOfFlarum OAuth: Unauthenticated account takeover via unverified email trust in Discord OAuth provider
Not ratedosv:CVE-2026-92161FriendsOfFlarum OAuth: Unauthenticated account takeover via unverified email trust in Discord OAuth provider
CriticalCVE-2026-92161FriendsOfFlarum Oauth: unzureichende Prüfung der Datenauthentizität
MediumCVE-2026-84048In der Erweiterung JoomGallery von joomgalleryfriends.
MediumCVE-2026-84048Joomgalleryfriends.net JoomGallery extension for Joomla: unzureichende Zugriffskontrolle

Other news entries

Devs to Anthropic, OpenAI, Cursor, and friends: Make security and privacy the defaultNewsThe Register — Security08.08.2026

Source: https://cloud.google.com/blog/topics/threat-intelligence/artex-and-friends-enter-agentic-offensive-frameworks/

More on Friends

Other advisories

Other news entries