{"slug": "protocol-level-attacks-on-agentic-commerce-platforms-taxonomy-and-defense", "title": "Protocol-Level Attacks on Agentic Commerce Platforms: Taxonomy and Defense", "summary": "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.", "body_md": "# Computer Science > Cryptography and Security\n\n[Submitted on 23 Jul 2026]\n\n# Title:Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense\n\n[View PDF](/pdf/2607.21824)\n\n[HTML (experimental)](https://arxiv.org/html/2607.21824v1)\n\nAbstract: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.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/protocol-level-attacks-on-agentic-commerce-platforms-taxonomy-and-defense", "canonical_source": "https://arxiv.org/abs/2607.21824", "published_at": "2026-07-28 04:07:08+00:00", "updated_at": "2026-07-28 04:22:17.889599+00:00", "lang": "en", "topics": ["ai-safety", "ai-agents", "ai-infrastructure"], "entities": ["AIP-Bench", "PCAT"], "alternates": {"html": "https://wpnews.pro/news/protocol-level-attacks-on-agentic-commerce-platforms-taxonomy-and-defense", "markdown": "https://wpnews.pro/news/protocol-level-attacks-on-agentic-commerce-platforms-taxonomy-and-defense.md", "text": "https://wpnews.pro/news/protocol-level-attacks-on-agentic-commerce-platforms-taxonomy-and-defense.txt", "jsonld": "https://wpnews.pro/news/protocol-level-attacks-on-agentic-commerce-platforms-taxonomy-and-defense.jsonld"}}