Security Analysis of Agentic AI Communication Protocols: A Comparative Evaluation

TL;DR

This paper conducts a comprehensive security evaluation of two agent communication protocols, revealing strengths and vulnerabilities, and proposes a hybrid approach to enhance security in multi-agent AI systems.

Contribution

It provides the first empirical comparison of CORAL and ACP security protocols, identifying specific architectural strengths and implementation weaknesses.

Findings

CORAL has strong transport-layer validation but critical implementation vulnerabilities.

ACP's flexibility leads to significant integrity and confidentiality flaws.

Existing protocols are currently insufficiently secure for practical deployment.

Abstract

Multi-agent systems (MAS) powered by artificial intelligence (AI) are increasingly foundational to complex, distributed workflows. Yet, the security of their underlying communication protocols remains critically under-examined. This paper presents the first empirical, comparative security analysis of the official CORAL implementation and a high-fidelity, SDK-based ACP implementation, benchmarked against a literature-based evaluation of A2A. Using a 14 point vulnerability taxonomy, we systematically assess their defenses across authentication, authorization, integrity, confidentiality, and availability. Our results reveal a pronounced security dichotomy: CORAL exhibits a robust architectural design, particularly in its transport-layer message validation and session isolation, but suffers from critical implementation-level vulnerabilities, including authentication and authorization failures at its SSE gateway. Conversely, ACP's architectural flexibility, most notably its optional JWS enforcement, translates into high-impact integrity and confidentiality flaws. We contextualize these findings within current industry trends, highlighting that existing protocols remain insufficiently secure. As a path forward, we recommend a hybrid approach that combines CORAL's integrated architecture with ACP's mandatory per-message integrity guarantees, laying the groundwork for resilient, next-generation agent communications.