DESET How it works
Click any part of the diagram
request / response
request / response
DESET AI app
Our proxy sits between the input and your model, like a firewall. It checks every request and response and blocks prompt injection, data leaks and unsafe actions.
What we test for
Prompt injection
Instructions hidden in user input, documents or web pages that take over your model or make it ignore its own rules.
Data leakage
Your system prompt, customer data or secrets ending up in an answer.
Unsafe actions
Agents calling tools, running commands or sending data they shouldn't.
Hallucinations
The model confidently making up facts, policies or prices and presenting them to your users as true.