Beyond the Mandate: A Systematic Security Analysis of the Agent Payments Protocol (AP2)

arXiv:2608.23858 · cs.CR, cs.AI · Submitted 2026-08-24 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-08-24

Updated: 2026-08-24

Code: https://github.com/mrwadams/stride-gpt

Terminology

• Verifier — 26× in this paper · explained in 2 episodes
• Actor — 24× in this paper · explained in 3 episodes
• Verification — 15× in this paper · explained in 2 episodes
• Accountability — 9× in this paper · explained in 2 episodes
• Shopping Agent — 7× in this paper
• Agentic AI — 5× in this paper · explained in 1 episode
• Core — 5× in this paper · explained in 2 episodes
• Model Context Protocol — 5× in this paper
• Provenance — 5× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Merchant Agent — 3× in this paper
• Ablation study — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Agent Interactions — 2× in this paper · explained in 1 episode
• Contextual Awareness — 2× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Model Context Protocol (MCP) — 2× in this paper · explained in 8 episodes
• Trusted Surface — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Agentic AI Risk Score — 1× in this paper
• Analyzer — 1× in this paper · explained in 1 episode
• Artificial Intelligence Vulnerability Scoring System — 1× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Credential Provider — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Merchant Payment Processor — 1× in this paper
• RAG — 1× in this paper · explained in 3 episodes
• Verifiability — 1× in this paper · explained in 2 episodes

Sources

• Secure Autonomous Agent Payments: Verifying Authenticity and Intent in a Trustless Environment
• ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications
• STRIDE-AI: A Threat Modeling Framework for Generative AI Security Assessment
• Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection
• Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
• Inter-Agent Trust Models: A Comparative Study of Brief, Claim, Proof, Stake, Reputation and Constraint in Agentic Web Protocol Design-A2A, AP2, ERC-8004, and Beyond
• Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning
• Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation
• Zero-Trust Runtime Verification for Agentic Payment Protocols: Mitigating Replay and Context-Binding Failures in AP2
• Security Analysis of Agentic AI Communication Protocols: A Comparative Evaluation
• Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
• SoK: Security of Autonomous LLM Agents in Agentic Commerce
• Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies
• Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs