paperAugust 2026Unreviewed

Whispers of Wealth: A Systematic Red-Teaming Study of the Agent Payments Protocol (AP2)

Tanusree Debi, Wentian Zhu

2026 International Conference on Intelligent Multimedia, Networking, and Security (IMNS)

Abstract

Large language model (LLM)-based agents are increasingly used to automate financial transactions, but their reliance on contextual reasoning introduces new security risks. The Agent Payments Protocol (AP2) secures agent-mediated purchases through cryptographically signed mandates; however, its robustness against reasoning-layer attacks remains unclear. This paper presents a systematic red-teaming evaluation of AP2 and identifies vulnerabilities arising from prompt injection. Two attack technique

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

NIST AI Risk Management Framework

MEASUREMeasure

Suggested from the entry's categories.

Cite

@inproceedings{debi2026whispers,
  title = {{Whispers of Wealth: A Systematic Red-Teaming Study of the Agent Payments Protocol (AP2)}},
  author = {Tanusree Debi and Wentian Zhu},
  year = {2026},
  month = aug,
  booktitle = {2026 International Conference on Intelligent Multimedia, Networking, and Security (IMNS)},
  doi = {10.1109/IMNS67862.2026.11655291},
  url = {https://www.semanticscholar.org/paper/ad5348c7ef25e740afae709cb6bd799d38b5d7ab}
}