The amount of training days lost to injury during military training has highlighted the need to identify a screening tool to predict injury. One hundred and fifty-eight female soldiers from the Combat Fitness Instructor Course (CFIC) of the Israel Defense Forces volunteered to participate in this study. All soldiers were free of orthopedic and neurologic conditions for at least one month before the study. All participants performed a battery of measurements during the first week of the course. Measures included anthropometric, functional movement screen (FMS), power performances (counter movement jump [CMJ], drop jump, single leg triple hop jump [SLTH], 10-m sprint) and a 2K run. Injury data was collected throughout the 3 month course. Median tests were used to compare between injured/non-injured soldiers. Chi-square and/or logistic regression analysis was used to examine the association between various predictors and injury. Percent body fat [%BF] was higher (p = 0.04), distance for SLTH was less for both left and right legs (p = 0.029, p = 0.047 respectively) and 2K run was slower (p =0.044) in injured compared to non-injured soldiers. No differences between groups were noted in total FMS score, however more zero scores in one or more movement pattern were found in the injured group (51.35 % vs. 30.5% p=0.0293). Only %BF, 2K run and SLTH distance were significant predictors of injury (p = 0.05, p = 0.02, p =0.016 respectively). The results of this study indicated that the FMS total score is not a predictor of injury in female soldiers in a CFIC. We found that %BF, SLTH, 2K run time, 10 meter sprint time and zero scores differentiated between injured and non-injured soldiers. In addition, %BF, 2K run and SLTH were each found to be separate predictors of injury. Further research is needed to determine threshold scores that predict injury.