In this article, we show how the copula-GARCH approach can be appropriately used to investigate the conditional dependence structure between the crude oil and natural gas markets as well as to derive implications for portfolio risk management in extreme economic conditions. Using daily price data from January 1997 to October 2011, our in-sample results show evidence of asymmetric dependence between the two markets. The crude oil and gas markets tend to comove closely together during bullish periods, but not at all during bearish periods. Moreover, taking the extreme comovement into account leads to an improvement in the accuracy of the out-of-sample Value-at-Risk forecasts.