In this paper, we propose two potential risk indicators to define and evaluate the safety of bicycle path at the microscopic level. Field bicycle data were collected from three survey sites under different traffic conditions. These two risk indicators based on speed dispersion were proposed and calculated during each 5-min interval. The risk influences of various widths of bicycle path and traffic conditions were analyzed by using one-way ANOVA. We further proposed a generalized linear model (GLM) for modeling and analyzing the relationships between bicycle risks and v/c ratio and percentages of electric bicycles, male cyclists, young cyclists, and loaded cyclists. The stepwise regression models were applied for determination of coefficients. The results show that the influences of gender and age of cyclists on potential risks are not significant. The risks increase with the width of bicycle path and percentage of electric bicycles, while only for wider bicycle path (4-lane case in this study), the risks are associated with whether or not cyclists are loaded. The findings could contribute for analysis and evaluation of the safety for bicycle path.