Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm

2025-07-10

AI Summary

This paper systematically investigates novel autonomy-related security risks arising from AI agents’ integration with cryptocurrencies and smart contracts. We identify threat vectors—including automated attacks, economic manipulation, and protocol-level abuse—that emerge when AI agents gain direct asset control. To address this, we propose the first risk taxonomy specifically designed for AI–blockchain convergence. Using qualitative analysis and multi-scenario adversarial reasoning, grounded in cryptoeconomic principles, we model risk propagation mechanisms and identify six canonical attack patterns (e.g., on-chain ransomware, liquidity hijacking, governance takeover). Our analysis reveals a unique “permission amplification effect” wherein AI agents exponentially magnify privileged capabilities within decentralized systems. Beyond characterization, the work pioneers new technical directions for detecting, constraining, and formally verifying AI-driven on-chain risks. It thus establishes foundational theory and actionable guidance for joint AI safety and Web3 governance.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Security and Privacy: Cryptocurrency and smart contracts
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

There is growing interest in giving AI agents access to cryptocurrencies as well as to the smart contracts that transact them. But doing so, this position paper argues, could lead to formidable new vectors of AI harm. To support this argument, we first examine the unique properties of cryptocurrencies and smart contracts that could lead to these new vectors of harm. Next, we describe each of these new vectors of harm in detail. Finally, we conclude with a call for more technical research aimed at preventing and mitigating these harms and, thereby making it safer to endow AI agents with cryptocurrencies and smart contracts.

Problem

• AI agents accessing cryptocurrencies create new harm risks
• Smart contracts amplify potential AI-related financial threats
• Technical solutions needed to mitigate AI-crypto interaction dangers

Innovation

• Examining cryptocurrency and smart contract risks
• Detailing new AI harm vectors
• Advocating technical harm prevention research