Attack Lab
Pick an attack, try it, then switch on the fix and try the same thing again. Everything here is a simulation that runs in your browser: the "server", the "database" and the "AI model" are a few lines of JavaScript on this page, so results are the same every time and no real system is touched. Each lab links to the framework entry it belongs to on the security frameworks pages.
Read next
- Containing AI Agents: A Defense-in-Depth Architecture for ProductionGeneric agents can do anything — which is exactly the problem. Custom agents in containers behind an inference proxy create a production architecture where security is …
- Keep Shipping: How to Say Yes to AI Agents Without Losing ControlAI agent projects don't die on cost. They die on trust. Blocking agents only works if you can identify them, and point tools can't secure agents. Only a platform can, at …
- Building the Agentic Enterprise: From Protocol Hype to Production-Grade AI AgentsThe agentic enterprise is real. But getting there requires a shift from generic protocol-based integrations to purpose-built agents with native tooling, embedded …