We propose an approach to enhance the fault diagnosis in black-box component-based systems, in which only events on component interfaces are observable, and assume that causal dependencies between component interface events within components are not known. For such systems, we describe a causality analysis framework that helps us establish the causal relationship between component failures and system failures, given an observed system execution trace. The analysis is based on a formalization of counterfactual reasoning, and applicable to real-time systems. We illustrate the analysis with a case study from the medical device domain.