The paper presents a systematic security analysis of Google’s Agent Payments Protocol (AP2) version 2.0, focusing on its roles, transaction lifecycle, and deployment architectures. It identifies 48 threats across five attack families, scores them with the AIVSS, and demonstrates eight high‑risk threats with proof‑of‑concept attacks and mitigations. The study also introduces a deployment‑aware scanner to map threats to various checks, showing that signed mandates alone cannot guarantee user intent when pre‑authorization context is manipulated.
By Avital Aviv, Parth A. Gandh, Ron Bitton, Asaf Shabtai
arXiv:2609.14744v2 Announce Type: replace
Abstract: By acquiring compute, credentials, accounts, services, and other agents, autonomous AI agents can introduce new authority into a task. Payment, bud...
By Genliang Zhu (Accentrust, Georgia Institute of Technology), Chu Wang (Accentrust, University of Illinois Urbana-Champaign)
AcquireBound is a runtime authorization framework that ensures AI agents can safely acquire and activate resources such as compute, credentials, and services. It quarantines acquired outputs, resolves their capabilities through authenticated evidence, and activates them only after verifying a manifest, provenance, and relational constraints. The system demonstrates strong safety properties, passing extensive benign and unsafe trace tests across multiple resource classes.
By Genliang Zhu
The paper surveys how decentralized agent economies combine independently designed protocols into a single task workflow, often leading to correct steps that still yield incorrect outcomes. It categorizes security and economic requirements into 17 property families across six stages, evaluates 12 systems and standards, and introduces the guarantee‑closure criterion to assess whether early guarantees persist to later stages. Empirical analysis of 840 executions and 11,648 checks reveals frequent failures between verification and settlement, highlighting gaps between recorded approvals and actual task conformance.
By Rui Sun, Xihan Xiong, Qin Wang, Fei Gao, Zelin Li, Zehua Cheng, Jiahao Sun, Zhipeng Wang
arXiv:2607. 21325v1 Announce Type: cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight.
By M. Llamb\'i-Morillas, D. Fern\'andez-Fern\'andez
arXiv:2607. 21325v2 Announce Type: replace-cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight.
By M. Llamb\'i-Morillas, D. Fern\'andez-Fern\'andez