Natural phenomena in mountains put people and assets at risk. Risk level is often described as a combination of hazard and vulnerability. Hazard relates to the intensity and frequency of phenomena while vulnerability concerns damages and values assessment. Risk assessment implies to combine those two components and propose risk reduction measures and strategies. In the debris-flows context, numerical models are used to assess height, speed and extent of flow. Others information sources such as historical data, expert assessments are also used to take a decision about the hazard level. One important issue is therefore to consider in an integrated framework the information imperfection resulting from those heterogeneous sources. In this article, we present and discuss an uncertainty analysis based on a numerical modelling of a debris-flows phenomenon. We present a methodology to propagate the uncertainty through numerical simulation models based on an “hybrid” approach. To consider the different aspects of information imperfection, especially its imprecision (lack of information, inaccuracy of mesure…), the “Hybrid” method of uncertainty analysis generalizes, under some restrictive conditions, the usual Monte Carlo method, by using theories for uncertainty and information management such as probability theory, possibility theory and belief function theory, used as tools for coding sets of probability densities.