SoK: Security of Autonomous LLM Agents in Agentic Commerce
SoK: Безопасность автономных LLM-агентов в агентной торговле
2026-04-15
SCID: 54.1/kv3yb3pp
Discuss with AI
agent payment protocolsagentic commerceautonomous LLM agentscross-layer securitytransaction authorization
Figures from the paper
Abstract (AI)
Autonomous large language model (LLM) agents such as OpenClaw are pushing agentic commerce from human-supervised assistance toward machine actors that can negotiate, purchase services, manage digital assets, and execute transactions across on-chain and off-chain environments. Protocols such as the Trustless Agents standard (ERC-8004), Agent Payments Protocol (AP2), OKX Agent Payments Protocol (APP), the HTTP 402-based payment protocol (x402), Agent Commerce Protocol (ACP), the Agentic Commerce standard (ERC-8183), and Machine Payments Protocol (MPP) enable this transition, but they also create an attack surface that existing security frameworks do not capture well. This Systematization of Knowledge (SoK) develops a unified security framework for autonomous LLM agents in commerce and finance. We organize threats along five dimensions: agent integrity, transaction authorization, inter-agent trust, market manipulation, and regulatory compliance. From a systematically curated public corpus of academic papers, protocol documents, industry reports, and incident evidence, we derive 12 cross-layer attack vectors and show how failures propagate from reasoning and tooling layers into custody, settlement, market harm, and compliance exposure. We then propose a layered defense architecture addressing authorization gaps left by current agent-payment protocols. Overall, our analysis shows that securing agentic commerce is inherently a cross-layer problem that requires coordinated controls across LLM safety, protocol design, identity, market structure, and regulation. We conclude with a research roadmap and a benchmark agenda for secure autonomous commerce.
Key Findings
1
A layered defense architecture, research roadmap, and benchmark agenda are proposed to address authorization gaps and secure autonomous commerce.
2
Analysis of a curated corpus identifies 12 cross-layer attack vectors affecting reasoning, tooling, custody, settlement, markets, and compliance.
3
It organizes threats into five dimensions: agent integrity, transaction authorization, inter-agent trust, market manipulation, and regulatory compliance.
4
The SoK introduces a unified security framework for autonomous LLM agents operating in commerce and finance.
5
The study shows that failures can propagate across system layers, exposing limitations in existing agent-payment security frameworks.
Research Object
autonomous LLM agents operating in agentic commerce and finance across on-chain and off-chain environments
Research Subject
cross-layer security threats, attack vectors, failure propagation, and defense requirements affecting agent integrity, transaction authorization, inter-agent trust, market manipulation, and regulatory compliance
Publication Details
Publication Date
2026-04-15
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest