Separating Disclosure from Authorization: Field-Tier Minimization for Agent Action Mediation

arXiv:2608.25474 · cs.CR, cs.SE · Submitted 2026-08-26 · Read on arXiv

cs.CR, cs.SE

Submitted: 2026-08-26

Updated: 2026-08-26

Code: https://github.com/Aurite-ai/agent-verifier

Terminology

• Verifier — 8× in this paper · explained in 2 episodes
• AI Agents — 4× in this paper · explained in 2 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Accountability — 3× in this paper · explained in 2 episodes
• Formal Methods — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• JSON Canonicalization Scheme — 1× in this paper
• Provenance — 1× in this paper · explained in 3 episodes
• Secure Production Identity Framework for Everyone — 1× in this paper
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems
• Cedar: A New Language for Expressive, Fast, Safe, and Analyzable Authorization (Extended Version)
• AI Identity: Standards, Gaps, and Research Directions for AI Agents

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs