↓ Skip to main content

Prompt Injection Arena

Read next: Containing AI Agents: A Defense-in-Depth Architecture for Production All playgrounds · Articles · Subscribe

Every other attack simulation on this site is scripted. This one isn't: a real language model (Qwen 3.5, 2 billion parameters) runs on your own device and plays Sol, the support assistant of a made-up bike shop. Your job is to make it misbehave, first by leaking a secret past four kinds of defence, then by hijacking its refund tool with nothing but a customer email. The model is small and unpredictable, so an attack that fails once may work the second time, just like against real systems.

Checking your browser…

Got the code in pieces or encoded?

What this shows. The defences in the levels all work inside or around the model: rules in the prompt, a filter on the output, a second model as a guard, tags around untrusted text. Each one makes attacks harder, and each one can be talked past. The switches marked in amber in the defences lab work outside the model: a secret it never sees can't leak, and a refund limit enforced in code can't be argued with. That's the lesson of the OWASP Top 10 for AI: assume injection sometimes succeeds, and limit what a hijacked model can reach and do.

Want the scripted versions, with the attack steps explained? Try the Attack Lab. Building a career in AI security? The careers pages and learning tracks show where this fits.

Everything on this page is fictional: Fjordline Bikes, Sol, the codes and the refunds. The model runs locally; this page sends nothing about your messages to any server.

Read next

Share this article