Blog
AI Research
GPT-5.5 and XBOW: A Step Change in Autonomous Application Security
Christopher FordAI Research
Mythos and GPT-5.5 Will Find a Lot of Vulnerabilities. Is That Enough?
Suzanne CicconeProduct
Getting to “Should I?”, Instead of “Can I?”: How XBOW Finds IDORs With High Accuracy in Ambiguous Contexts
Alvaro MuñozOffensive Security Academy
Ethical Considerations in AI-Driven Penetration Testing: A Governance Framework for Security Teams
XBOW TeamSecurity Research
Dead.Letter (CVE-2026-45185) How XBOW Found an Unauthenticated RCE on Exim
Federico Kirschbaum, Andres LuksenbergSecurity Research
Mythos for Offensive Security: XBOW's Evaluation
Albert ZieglerOffensive Security Academy
10 Red Flags to Investigate When Evaluating AI Pentesting Vendors
XBOW TeamOffensive Security Academy
What Is Insecure Direct Object Reference (IDOR), and How Do You Test for It?
XBOW TeamOffensive Security Academy
