# Two new papers show how authority leaks when AI agents sign payments and hand tasks to other agents

The research arrives as OpenAI chief executive Sam Altman reportedly told a New York Times conference that handing control to AI is "a terrible idea."

- Published: 2026-11-20T06:11:13.056Z
- Canonical: https://polylog.news/ai/2026-11-20/two-new-papers-show-how-authority-leaks-when-ai-agents-sign
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.CR](https://arxiv.org/abs/2611.24989), [arXiv cs.CR](https://arxiv.org/abs/2611.25056), [Polylog editors](https://polylog.news)

A paper posted to arXiv on November 20, "Signed, Valid, and Unauthorized", studies the boundary between agent commerce protocols and crypto wallets. These protocols let software agents pay in stablecoins. A buyer approves a payee, an asset,…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-20/two-new-papers-show-how-authority-leaks-when-ai-agents-sign (subscription information: https://polylog.news/pricing).