Autonomous Vehicle architectures fuse legacy, electro-mechanical components with advanced sensor technology and digital controllers, governed by software. An open challenge for the design of autonomous vehicles are cyber threats such as Electromagnetic Injection (EMI) attacks, to the low-level layer, comprising electro-mechanical components, which can propagate through to the higher-level, intelligent control, affecting decision-making and the safety of the vehicle. This study analyses the robustness of the design of the software stack of a real-world Autonomous Vehicle to EMI attacks on the steering angle sensor. To achieve this, we create a hybrid testbed which combines the mathematical model of the low-level sensor with the high-fidelity, intelligent control. We further develop safety and performance metrics, measured at the high-level, which we use to generate a detailed view on the safety and system performance of the software. We conduct diverse EMI attacks on the target AV, within 3 diverse critical driving scenarios, consisting > 1000 simulations. The results indicate a correlation between an increase in attack noise with an increase in safety violations and failures to complete the mission of the AV. Our results highlight the importance, for AV software developers, of testing under diverse attack and driving scenarios, as each scenario within our experimentation exhibits different behaviour of the system and correlations to differing safety and system performance indicators.