AI agents now pause for approval before they send money, delete files or email outsiders, and that approval is usually treated as a second factor. We argue it is one only when compromising the agent cannot produce it and when it names exactly what it approves, and we test both conditions. We define twelve attacks on the approval path, including decoy recipients, amount cancellation, card padding, label spoofing, enrollment squatting and threshold splitting, and run them against the Agent Payments Protocol (AP2), the Microsoft action-bound approval design and Model Context Protocol (MCP) elicitation. An audit of ten agent runtimes finds no third-party verifiable approval record, no flood limits where measurable, and post-approval argument changes in four of eight runtimes with measurable binding. As a reference defense we build ASU (Agent Step-Up), a gateway that renders the approval card from a canonical effect descriptor, has a passkey on the phone of the user sign its digest, and executes only the stored call. Tamarin proves its binding, single-use and key-level non-repudiation properties under three stated hypotheses (53 lemmas). Across 27,108 scripted trials and 609 AgentDojo attack pairs, ASU stops substitution, replay and grant stretching, and the trusted card cuts forged-narration attack success from 0.54 to 0.03. With 15 current language models as automated approvers, the trusted card raises the attack catch rate from 0.30 to 0.98, at the cost of refusing 16 percent of harmless near misses, mostly due to a placeholder artifact in our stimuli. A second device adds nothing measurable over a trusted on-host confirmation in these experiments, flooding still succeeds 0.45 to 0.60 of the time against a modeled approver, and approval cannot stop effects that policy already allows. Code, data and proofs: https://github.com/Sports-Vision-Inc/agent-step-up
Runtime Authorization Consistency Checking for MCP-based Agentic Workflows
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Fuxi Institution(伏羲研究院);Center for Internet Governance, Tsinghua University(清华大学互联网治理研究中心)
Agent Approval Laundering: Transitive Effects Beyond the Approved Invocation
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Beihang University(北京航空航天大学);State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(北京邮电大学网络与交换技术国家重点实验室)
NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations
School of Computing, Wichita State University(威斯康星州立大学计算机学院);Department of Computer Science, American International University-Bangladesh(孟加拉国国际大学计算机科学系)
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
School of Computer Science and Technology, Xidian University(西安电子科技大学计算机科学与技术学院);Shaanxi Key Laboratory of Network and System Security(陕西省网络与系统安全重点实验室);College of Cyber Security, Jinan University(暨南大学网络安全学院)
TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools
Harvard Medical School(哈佛医学院);MIT Lincoln Laboratory(麻省理工学院林肯实验室);Harvard University(哈佛大学);Broad Institute of MIT and Harvard(麻省理工学院与哈佛大学博德研究所);Harvard Data Science Initiative(哈佛数据科学倡议)
APEX: Active Protection at Execution Boundaries for LLM Agents
Tsinghua University(清华大学);Imperial College London(帝国理工学院);Nanjing University(南京大学);The Chinese University of Hong Kong(香港中文大学);University College London(伦敦大学学院);A*STAR(新加坡科技研究局);University of British Columbia(不列颠哥伦比亚大学);Shenzhen University(深圳大学);The University of Hong Kong(香港大学)