PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

XBOW Now Matches the Capabilities of a Top Human Pentester

xbow.com | blog | #ai-security | #pentesting | #benchmark | #offensive-security | #ai-pentesting | #human-vs-ai
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Head-to-head numbers: five pentesters versus XBOW on 104 original benchmarks — the principal tester matched XBOW's 85% solve rate, but XBOW needed 28 minutes to the humans' 40 hours.
Published
Collected

Related coverage

blog · xbow.com
Grok 4.7 Is Different. So Is the Best Way to Use It.
XBOW tested Grok 4.7 on exploit crafting and agentic pentests: inside xAI's Build it improved substantially over 4.6, outside Build it slipped slightly—orchestration now matters as much as prompts.
blog · xbow.com
How to Run an AI Application Pentesting Vendor RFP: The Evaluation Framework that actually works
An RFP evaluation framework for buying AI application pentesting: separating true autonomous testing from scanners and AI-assisted workflows, with questions, criteria and scoring guidance.
blog · aikido.dev
Aikido launches external network pentesting
TL;DR: Aikido now pentests your external network. Attackers already test your perimeter every day, and with AI agents doing the grunt work, they're faster than ever. Now you can run the same test first. Give our agents one domain and they'll map the internet-facing systems you run and attack them from the outside, exactly like a malicious actor would.
blog · aikido.dev
Adding Aikido AI pentesting to your existing security stack
How to add Aikido's AI pentesting on top of the SAST, SCA and cloud tools you already run, from your first pentest through whitebox testing, continuous testing and remediation.
blog · aikido.dev
Jason Haddix: Stop fearing AI pentesting
Aikido recaps Jason Haddix's Secure Disclosure episode: he predicts 90% of pentests will be done by AI, argues defenders must fight AI with AI, and says AI solves pentesting's coverage problem.
blog · aikido.dev
Jason Haddix: Stop fearing AI pentesting
Jason Haddix on why '90% of pen tests will be done by AI': AI solves pentesting's scale problem, scanners-in-disguise will fade, and defenders must fight AI with AI rather than fear it.
Back