Skip to main content

Secure Task-bound Agent Message Proof (STAMP) Protocol
draft-guy-bary-stamp-protocol-00

Document Type Expired Internet-Draft (individual)
Expired & archived
Author Guy Bary
Last updated 2025-11-02 (Latest revision 2025-04-27)
RFC stream (None)
Intended RFC status (None)
Formats
Stream Stream state (No stream defined)
Consensus boilerplate Unknown
RFC Editor Note (None)
IESG IESG state Expired
Telechat date (None)
Responsible AD (None)
Send notices to (None)

This Internet-Draft is no longer active. A copy of the expired Internet-Draft is available in these formats:

Abstract

The Secure Task-bound Agent Message Proof (STAMP) protocol provides a cryptographically verifiable delegation and proof framework for AI- driven multi-agent systems. STAMP introduces task-bound access tokens and message-level proofs for agentic environments, binding tokens to specific user intents, tasks, and agent identities. STAMP tokens ensure that delegation, execution, and agent-to-agent communication comply with least-privilege and zero-trust security principles. STAMP interoperates with OAuth 2.0, GNAP, and modern proof-of- possession (PoP) techniques, providing stronger security for dynamic, non-deterministic workflows involving autonomous agents.

Authors

Guy Bary

(Note: The e-mail addresses provided for the authors of this Internet-Draft may no longer be valid.)