Spring Security Third Edition Secure Your Web Applications Restful Services And Microservice Architectures -

If you take one concept from this book, make it this: “Authentication identifies who can knock. Authorization decides what they can touch. But in microservices, every internal call needs its own authorization – don’t trust the incoming token just because it’s signed.” Look at the book’s section on @CurrentSecurityContext to replace SecurityContextHolder boilerplate, and the chapter on reactive security for WebFlux – where even @PreAuthorize works differently than you expect.

Move @PreAuthorize to the service layer and use method security expressions that check both role and ownership: If you take one concept from this book,

@Service public class DocumentService { public Document findById(Long id) { // No security here! return documentRepository.findById(id); } } If any other service calls findById(1) – maybe from a scheduled job, a message listener, or another microservice – the authorization check is gone. Move @PreAuthorize to the service layer and use

Have you run into any of these three pitfalls in your own projects? The patterns above might just save your next security audit. The patterns above might just save your next security audit

// Simplified from Chapter 11 JwtAuthenticationToken token = ...; Set<String> allowedScopes = getScopesForCurrentService(); Jwt trimmedJwt = JwtHelper.trimScopes(token.getToken(), allowedScopes); This way, payment-service never sees scopes like profile:write – reducing lateral movement risk if compromised. The third edition isn’t about adding more filters. It’s about understanding where authorization actually happens – at the method level, between services, and even inside SQL queries (using Spring Data’s @PostFilter sparingly, as the book warns).

Sure, you removed HttpSession and added JWT tokens. But did you accidentally reintroduce state via your database? Every time you query a token_blacklist table or hit Redis to validate a session-like JWT, you’ve created state – and with it, scalability bottlenecks.