We propose a methodology for verifying security properties of network protocols at design level. It can be separated in two main parts: context and requirements analysis and informal verification; and formal representation and procedural verification. It is an iterative process where the early steps are simpler than the last ones. Therefore, the effort required for detecting flaws is proportional to the complexity of the associated attack. Thus, we avoid wasting valuable resources for simple flaws that can be detected early in the verification process. In order to illustrate the advantages provided by our methodology, we also analyze three real protocols.