Hack The Box launches AI cyber range & unveils red team certification

Hack The Box has unveiled what it describes as the world's first controlled AI cyber range. The new platform, called HTB AI Range, allows organisations to test and benchmark autonomous AI security agents in live-fire scenarios. The launch comes as AI agents play a growing role in both offensive and defensive cyber operations.

HTB AI Range aims to replicate the complexity of enterprise cyber environments. The platform features thousands of continuously updated targets designed for both attack and defence exercises. It is set up so AI agents and human operators can be evaluated side-by-side. Every participant-human or machine-is tested, refined, and retested until measurable mastery is achieved.

Urgent Demand

Recent incidents have highlighted an urgent need for cybersecurity teams to train against AI-enabled threats. There have been reports of state-backed attackers using highly autonomous AI models from Anthropic in operations, sometimes at up to 90% autonomy. This trend has broadened the attack surface organisations must defend and changed the threat landscape.

Hack The Box has seen AI agents perform strongly in some tasks. In a capture-the-flag (CTF) event held in April, autonomous AI teams successfully completed 19 out of 20 easy-level challenges, matching the results of hundreds of human teams. The AI teams struggled on more complex, multi-step problems, where human participants still had the edge. Attackers are already using AI to automate large volumes of requests. Financial, technology, manufacturing, and government sectors are among the most targeted. Defenders need to develop expertise to counter these AI-driven campaigns.

"AI is now part of the cyber battle and overall ecosystem, and we're building the arena where it can safely be tested and used to defend responsibly," said Haris Pylarinos, CEO and Founder, Hack The Box.

Industry Context

HTB AI Range is intended for enterprises, managed security providers, and governments. Users can run their AI models in complex simulated environments and measure performance against established frameworks. These include MITRE ATT&CK, NIST/NICE, and the OWASP Top 10. The new platform is designed as a step toward hybrid readiness, where human and AI defenders are trained together.

Gerasimos Marketos, Chief Product Officer at Hack The Box, explained the company’s approach. "We're addressing the urgent need to continuously validate AI systems in realistic operational contexts where stakes are high and human oversight remains vital. HTB AI Range makes that possible. It's the next step in building trust, safety and performance into AI for cyber defense," said Marketos.

Early research in the cybersecurity sector has shown that AI is now being used to automate aspects of reconnaissance and exploit discovery. These advances create new challenges for defenders. Training and validation must keep pace.

"AI is fundamentally reshaping the threat landscape. Early research is already showing how AI can automate reconnaissance and link potential exploit paths in ways that were extremely difficult just a year ago. As these capabilities mature, defenders will need teams trained to operate under more dynamic, real-world conditions. That's why I'm energized by the work Hack The Box is doing for the industry," said Dawn-Marie Vaughan, Global Offering Lead - Cybersecurity, DXC.

New Certification Path

Hack The Box also announced a new certification for AI Red Teamers, which will launch in early 2026. This credential complements an existing learning path developed with Google. The program aims to produce cybersecurity professionals capable of testing, evaluating, and securing AI systems across their entire lifecycle. The new certification will reflect the Secure AI Framework developed by Google, targeting an industry-standard approach for AI security expertise.

Hack The Box says the certification is a response to an observed skills gap. In a recent AI red-teaming CTF run by the company and HackerOne, fewer than half of registrants completed a single challenge. The new learning and certification programmes will address this gap for teams facing increasingly sophisticated AI threats.

HTB plans to make the AI Red Teamer certification available in the first quarter of 2026. The company expects it to set a new benchmark for assessing and upskilling AI security expertise at enterprise scale.