apisec builds a model of your application as a system: its third-party microservices, its call graph, its authorization boundaries, and the downstream APIs it depends on. Then it generates attacks specific to that system and executes them at runtime.
Not prompt trickery in isolation. Full chains: poison an input an application endpoint will read, watch which software path it calls next, follow that call into the API layer, and see what comes back out.
Applications are compositional. Each part looks defensible on its own; the chain is what breaks. Only an attacker working through the whole path finds it, and that's what apisec automates: authentication, authorization, and access control through the business-logic lens.
The complete exploit chain from entry point to data reached, with the blast radius and the prompt to resolve it.
Every step passes its own review. The chain is the breach. apisec runs it end-to-end and shows you the whole path.
apisec uses models to reason about your agents and to generate attacks. It does not use a model to decide whether an attack worked. Execution is the arbiter: deterministic, repeatable, replayable, auditable.
That matters more here than anywhere else you run. A system that behaves differently on every invocation cannot be governed by a tool that behaves differently on every invocation.
The free Surface tools produce what you need before an exploit run.