← Back to all news
arXiv AI By Sai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargill

Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization

Read the original on arXiv AI →

The paper "Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization" examines how AI agents seek approval before performing actions such as sending money or deleting files. It identifies twelve attack vectors on the approval process and evaluates them against several protocols, finding that many agent runtimes lack verifiable approval records and exhibit binding weaknesses. The authors propose a defense called ASU (Agent Step-Up), which renders a canonical approval card, requires a phone passkey, and enforces single-use execution, demonstrating strong protection against substitution, replay, and grant-stretching attacks in extensive simulations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 1

Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses

The paper investigates a critical flaw in AI coding-agent systems such as Claude Code, Codex CLI, and Cursor, where the action approved by a human is not the same as the action executed by the harness. It introduces the concept of Approval Laundering, categorizing six systematic failure modes—Scope, Argument, Temporal, Tool, Delegation, and Semantic laundering—and demonstrates these failures through controlled experiments. The authors propose an Approval Token mechanism that mitigates some laundering types but leaves others unaffected, highlighting the limitations of current enforcement strategies.

By Yang Wang
llmsagents
More like this →
arXiv AI
Sep 2

Delegation Without Trust: An Empirical Gap Analysis of Identity, Authorization, and Runtime Governance in Multi-Agent LLM Systems

The paper examines the security challenges of delegating authority to autonomous LLM agents that act on users’ behalf. It introduces a threat model with four adversaries and eight security requirements, demonstrates that current frameworks (LangGraph, CrewAI, AutoGen, MCP) fail to meet these standards, and presents an authorization broker that blocks all identified threats with minimal overhead. The broker is shown to resist numerous attacks and limits compromised sub‑agents to their delegated tasks, and its principles are implemented in VotalAI’s LLM Shield.

By Panduranga Sai Varma Dantuluri, Jyotirmoy Sundi
llmsagents
More like this →