Blog
AI Research
The OpenAI and Hugging Face Incident: When the Model Hacks the Test
Pre-release models escaped a sandbox and exploited real systems to win a benchmark, showing why powerful AI agents need external controls, strict scoping, and independent validation.
Nico Waisman
Security Research
The European Central Bank Just Made Autonomous Offensive Security a Board-Level Problem
Julian Totzek-HallhuberCompany News
Blackhat 2026: Hacking the Past. Hacking the Future.
Federico KirschbaumAI Research
Engineering the Impossible: Adding Safety to Autonomous Agents
Albert ZieglerOffensive Security Academy
Threat Hunting with AI: Why it Matters and the Role of Autonomous Pentesting Tools
XBOW TeamOffensive Security Academy
Why Choose AI Application Pentesting: Costs, Coverage, and Risk Reduction Compared
XBOW TeamOffensive Security Academy
Legal Boundaries of AI Penetration Testing: Engagements, Laws & Permissions
XBOW TeamAI Research
Grok 4.5 Is Powerful. The System Around It Makes It Safe.
Albert Ziegler, Maria KnorpsOffensive Security Academy
Post Purchase Guide: Is Your AI Pentesting Tool Actually Working? - 7-Step Renewal Decision Framework
XBOW TeamSecurity Research
