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
A Shell Is Worth a Thousand Images: Bing Images RCEs
Nico WaismanOffensive Security Academy
AI Pentesting vs Red Teaming: Finding Risk vs Testing Response
XBOW TeamOffensive Security Academy
BAS vs Red Team vs Pentesting: How to Choose the Right Security Test
XBOW TeamOffensive Security Academy
AI Pentesting Adoption Challenges for Enterprise: What’s Actually Getting in the Way
XBOW TeamAI Research
Grok 4.5 Poised To Take Over the Middle of the AI Security Market
Albert ZieglerOffensive Security Academy
Human-in-the-Loop AI Pentesting
XBOW TeamAI Research
The Rise of Affordable Models: Comparing GLM and Muse Spark on Cyber
Albert ZieglerOffensive Security Academy
Continuous Vulnerability Testing With a Small Team: A Practical Guide
XBOW TeamOffensive Security Academy
