Traditional transportation models inadequately account for how crime risk influences urban mobility decisions, treating safety as a secondary factor despite its significant impact on travel behavior. We develop a multi-task pipeline framework that simultaneously predicts five interconnected outcomes: crime counts, area-level risk classification, route safety assessment, transportation mode choice, and individual vulnerability. Our approach leverages shared feature engineering while maintaining task-specific models to capture complex crime-mobility interdependencies. Using the NetMob Challenge 2025 dataset containing 80,697 trips across 600 French geographic areas with integrated national crime statistics, we employ Random Forest models enhanced with interpretability analysis for actionable insights. The framework demonstrates strong predictive performance across all tasks: crime count regression (R \(^2\) = 0.847), crime risk classification (accuracy = 90.79%), route safety assessment (accuracy = 96.29%), and mode choice prediction (accuracy = 99.94%). Comprehensive feature analysis reveals geographic factors contribute 68.2% of predictive power, with temporal and demographic factors accounting for 18.5% and 13.3% respectively. Mode-specific analysis demonstrates that public transportation exhibits 52% higher crime associations than private alternatives, with subway systems showing the highest risk exposure. Gender-stratified results indicate women avoid high-risk areas 27% more frequently than men (p < 0.001), with disparities most pronounced during evening hours when safety concerns peak. These empirical findings translate into evidence-based recommendations for transportation planning, including dynamic security resource allocation and personalized safety guidance systems for vulnerable populations.