Security
Authorization Propagation in Agent2Agent Systems: An Experimental Security Evaluation of Multi-Hop Delegation
arXiv cs.MA0 views
arXiv:2611.07050v1 Announce Type: new Abstract: Delegated Agent2Agent (A2A) workflows create a security problem when the agent sending a request is different from the principal from which the authority originated. This paper evaluates a layered downstream-verification design in a synthetic four-party healthcare reimbursement workflow. The prototype separates current-caller context, transitive authorization evidence, per-hop Ed25519 request authentication, and independent replay state for requests and authorization artifacts. Of 15 adversarial conditions, 14 are rejected; an isolated delegation-path test exposes the absence of semantic authority attenuation. A separate authorized-intermediary experiment shows that a holder of the shared authorization-evidence HMAC key can modify the represented authority and generate valid evidence. In the fixed-depth local benchmark, the full configuration has a median security-processing latency of 5.11 ms and a 3.87 kB serialized payload. The results show the value of separating request authentication from inherited authority while identifying origin-verifiable delegation and semantic attenuation as requirements for stronger A2A authorization propagation.
Source:https://arxiv.org/abs/2611.07050PreviousDecentralized Sparse Quantile RegressionNextMore Agents, More Reliable? System-Level Reliability of Multi-Agent LLMs under Operational-Profile Uncertainty
Related posts
Patch Your Trilogy Too: SQL Injection
0dev.to
CVE-2026-115560 Evidence Review: What Operators Can Confirm Today
0dev.to PHP
PHP-FPM and Apache Response Planning for CVE-2026-115560
0dev.to PHP
Session Lifecycle Review for CVE-2026-115560 in PHP Applications
0dev.to PHP

Extend Claude Code to remote sessions on Amazon Bedrock AgentCore with security controls
0AWS Machine Learning Blog

How Greenlight Financial built an autonomous SOC solution on Amazon Bedrock AgentCore
0AWS Machine Learning Blog