The decentralized and disagreggated nature of the Open Radio Access Network (O-RAN) introduces novel vulnerabilities in the realm of security, particularly concerning wireless attacks. Among them, radio frequency (RF) jamming attacks emerge as a significant threat due to their simplicity and damage they might inflict. In the context of O-RAN applications, this threat is particularly dangerous for Vehicular Ad Hoc Networks (VANETs). To ensure the safety of those vehicles on the roads, a system to identify these threats must be build. In light of necessity, we propose the implementation of machine learning classification models with three distinct algorithms: K-nearest neighbor (KNN), Random Forest (RaFo), and XGBoost (eXtreme Gradient Boosting), for the detection of jamming attacks.