SUDP: Secret-Use Delegation Protocol for Agentic Systems
SUDP proposes a delegation protocol preventing agentic AI systems from holding reusable secrets, replacing today's 'authorisation by exposure' pattern with scoped, non-replayable credentials.
Summary written by editorial AI · Source link below
arXiv:2604.24920v4 Announce Type: replace Abstract: Agentic systems now act with user secrets for APIs, messaging platforms, and cloud services. Today's agent runtimes typically implement authorization by exposure: enabling action means placing a reusable secret, or a reusable artifact derived from it, inside the runtime, so a transient prompt-injection or tool-side compromise becomes durable account compromise. Existing defenses cover adjacent pieces such as secret storage, scoped delegation,
Editorial Analysis
As enterprises deploy AI agents with access to cloud APIs and secrets vaults, moving from raw-secret exposure to scoped delegation reduces blast radius of agent compromise.
Audit how your agentic systems currently receive and use secrets, and assess whether a delegation protocol like SUDP could reduce credential-exposure risk.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the AI Security Desk
- OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication1d
- Exposed Infrastructure Reveals How Ransomware Affiliates Used AI Agents to Execute Intrusions3d
- You gave your AI agent access, but who is giving it orders?3d
- AI Agents as Insider Threats: Inside Microsoft's Bet on a Unified Security Stack3d
- Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances3d