Protocol-Level Attacks on Agentic Commerce Platforms: Taxonomy and Defense

Researchers at an undisclosed institution identified 33 protocol-level vulnerabilities across three leading agentic commerce platforms, each achieving a 100% deterministic attack-success rate regardless of the AI model used, and demonstrated a chain of three vulnerabilities enabling end-to-end payment hijack. The team introduced AIP-Bench, the first deterministic benchmark for agentic commerce security, and PCAT, a platform-agnostic defense that reduced structural attack-success rates to zero for four of five vulnerability classes without modifying any platform.

Computer Science Cryptography and Security Submitted on 23 Jul 2026 Title:Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense View PDF /pdf/2607.21824 HTML experimental https://arxiv.org/html/2607.21824v1 Abstract:Agentic commerce platforms let AI agents autonomously discover services, move payments, and wield user credentials on their users' behalf, and they already handle real money. Their security has so far been studied almost entirely at the level of the AI model, through prompt injection and misalignment. We show that the more consequential risks lie one layer down, in the protocol between agents and commerce services. There, vulnerabilities are structural : exploitation is deterministic and ndependent of which model an agent runs, so no model improvement removes them. Across three leading platforms we identify 33 such vulnerabilities, each succeeding deterministically regardless of the deployed model, at a 100% attack-success rate ASR wherever live-measured. The same failure modes recur across independently built codebases, a systemic pattern rather than isolated bugs. Three of them chain into an end-to-end payment hijack. We contribute a taxonomy separating these structural attacks from model-dependent semantic ones. We also build two artifacts: AIP-Bench Agent Interaction Protocol Benchmark , to our knowledge the first deterministic benchmark for agentic commerce security, and PCAT Protocol-level Commerce Agent Trust , a platform-agnostic defense that drives the structural attack-success rate to zero for four of the five structural classes RC-1, RC-2, RC-4, RC-5 , with RC-3 observable credential channels reduced to warn-only, without modifying any platform. Agentic commerce must be secured at the protocol layer, not only the model. References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .