Security Risks of Agentic Vehicles: A Systematic Analysis of Cognitive and Cross-Layer Threats

Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles (AgVs), with capabilities such as memory-based personalization, goal interpretation, strategic reasoning, and tool-mediated assistance. While frameworks such as the OWASP Agentic AI Security Risks highlight vulnerabilities in reasoning-driven AI systems, they are not designed for safety-critical cyber-physical platforms such as vehicles, nor do they account for interactions with other layers such as perception, communication, and control layers. This paper investigates security threats in AgVs, including OWASP-style risks and cyber-attacks from other layers affecting the agentic layer. By introducing a role-based architecture for agentic vehicles, consisting of a Personal Agent and a Driving Strategy Agent, we will investigate vulnerabilities in both agentic AI layer and cross-layer risks, including risks originating from upstream layers (e.g., perception layer, control layer, etc.). A severity matrix and attack-chain analysis illustrate how small distortions can escalate into misaligned or unsafe behavior in both human-driven and autonomous vehicles. The resulting framework provides the first structured foundation for analyzing security risks of agentic AI in both current and emerging vehicle platforms.

Key Contributions

• Role-based agentic vehicle architecture decomposing responsibility into a Personal Agent and Driving Strategy Agent with defined trust boundaries
• Structured threat taxonomy covering cognitive vulnerabilities (memory poisoning, intent manipulation, tool misuse, goal hijacking) and cross-layer attack propagation from perception/communication/control layers
• Severity matrix and attack-chain analysis showing how small upstream distortions escalate into misaligned or unsafe agentic driving behavior

🛡️ Threat Analysis

Details

Similar Papers