Paper 2026/1674

MinMandate: Task-Hiding Payment Authorization for Web Agents

Ge Gao, Harbin Institute of Technology
Haining Yu, Harbin Institute of Technology
Zhichao Liu, Harbin Institute of Technology
Dongyang Zhan, Harbin Institute of Technology
Yuanxiao Zhu, Harbin Institute of Technology
Zhongyun Hua, Harbin Institute of Technology
Abstract

AI agents increasingly pay for Web services on behalf of their users to complete complex tasks. Such a task needs many payments, and the user usually must approve each one, forcing the agent to stop at every payment. Mechanisms such as the Agent Payments Protocol (AP2) therefore enable the user to sign one payment mandate in advance that bounds the agent's payments for the task. However, whoever checks the mandate can learn the task, which is often sensitive. Specifically, (1) the user's wallet can see the full mandate when it checks each payment, so it can trace every payment to the task; and (2) although each merchant sees only the payment it receives, it verifies that payment under a signing key that repeats across the task, so colluding merchants can link the payments and reconstruct the task. We present MinMandate, a task-hiding payment authorization system for AI agents in which the user approves a task-bounded payment mandate once. In MinMandate, the wallet checks each payment through a constant-size keyed-verification policy credential, which reveals neither what the mandate allows nor which mandate the payment comes from. Each merchant then accepts the wallet's one-time ticket as proof of payment and never sees the mandate or its signing key. Formally, we prove authorization soundness and unlinkability in our threat model. Our experiments show that the overhead of MinMandate is practical, with a payment taking 197 ms and under half of AP2's bytes. Notably, MinMandate cuts wallet-side tracing from every payment under AP2 to the level of random guessing. Moreover, from their own payment-request records alone, colluding merchants can reconstruct the user's task in 47% of the cases under AP2 but in only 8% under MinMandate.

Metadata
Available format(s)
PDF
Category
Cryptographic protocols
Publication info
Preprint.
Keywords
agentic paymentsdelegated payment authorizationkeyed-verification anonymous credentialsunlinkabilityAI agents
Contact author(s)
gaoge92021 @ gmail com
History
2026-10-31: revised
2026-08-13: received
See all versions
Short URL
https://ia.cr/2026/1674
License
Creative Commons Attribution-NonCommercial-NoDerivs
CC BY-NC-ND

BibTeX

@misc{cryptoeprint:2026/1674,
      author = {Ge Gao and Haining Yu and Zhichao Liu and Dongyang Zhan and Yuanxiao Zhu and Zhongyun Hua},
      title = {{MinMandate}: Task-Hiding Payment Authorization for Web Agents},
      howpublished = {Cryptology {ePrint} Archive, Paper 2026/1674},
      year = {2026},
      url = {https://eprint.iacr.org/2026/1674}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.