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

arXiv: https://arxiv.org/abs/2507.08249 · HTML: https://mlsanity.com/paper/2507.08249/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 224 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Builds on (most cited first, 30 of 37)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Scalable agent alignment via reward modeling: a research direction](https://mlsanity.com/paper/1811.07871/) (2018)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [The Alignment Problem from a Deep Learning Perspective](https://mlsanity.com/paper/2209.00626/) (2022)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation](https://mlsanity.com/paper/1802.07228/) (2018)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Are Emergent Abilities in Large Language Models just In-Context Learning?](https://mlsanity.com/paper/2309.01809/) (2023)
- [Evaluating Language-Model Agents on Realistic Autonomous Tasks](https://mlsanity.com/paper/2312.11671/) (2023)
- [Feedback Loops With Language Models Drive In-Context Reward Hacking](https://mlsanity.com/paper/2402.06627/) (2024)
- [LLM Agents Making Agent Tools](https://mlsanity.com/paper/2502.11705/) (2025)
- [Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models](https://mlsanity.com/paper/2403.04786/) (2024)
- [Tools Fail: Detecting Silent Errors in Faulty Tools](https://mlsanity.com/paper/2406.19228/) (2024)
- [Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents](https://mlsanity.com/paper/2503.16248/) (2025)
- [The Reasons that Agents Act: Intention and Instrumental Goals](https://mlsanity.com/paper/2402.07221/) (2024)
- [Position: Key Claims in LLM Research Have a Long Tail of Footnotes](https://mlsanity.com/paper/2308.07120/) (2023)
- [LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management](https://mlsanity.com/paper/2501.00826/) (2025)
- [Dissecting Ponzi schemes on Ethereum: identification, analysis, and impact](https://mlsanity.com/paper/1703.03779/) (2017)
- [Charting the Landscape of Online Cryptocurrency Manipulation](https://mlsanity.com/paper/2001.10289/) (2020)
- [Eliza: A Web3 friendly AI Agent Operating System](https://mlsanity.com/paper/2501.06781/) (2025)
- [The Art of The Scam: Demystifying Honeypots in Ethereum Smart Contracts](https://mlsanity.com/paper/1902.06976/) (2019)
- [Security Threats in Agentic AI System](https://mlsanity.com/paper/2410.14728/) (2024)
- [A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading](https://mlsanity.com/paper/2407.09546/) (2024)
- [Increased Compute Efficiency and the Diffusion of AI Capabilities](https://mlsanity.com/paper/2311.15377/) (2023)
- [Forsage: Anatomy of a Smart-Contract Pyramid Scheme](https://mlsanity.com/paper/2105.04380/) (2021)

## Built on by (most cited first, 3 of 3)

- [PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance](https://mlsanity.com/paper/2608.17220/) (2026)
- [Is Decentralized AI Governable? From Regulative Policy to Constitutive Protocol](https://mlsanity.com/paper/2605.24538/) (2026)
- [When AI Agents Meet MEV: Cross-Chain Arbitrage in the Agentic Economy](https://mlsanity.com/paper/2609.17897/) (2026)

## Abstract (arXiv)

There is growing interest in giving AI agents access to cryptocurrencies and smart contracts. But doing so, this position paper argues, could spawn categorically new vectors of AI harm. To support this notion, we first examine the unique technical properties of cryptocurrencies and smart contracts that, when paired with AI agents, make this so. Next, we describe three of these new vectors of AI harm in detail, providing a first-of-its-kind taxonomy. Finally, we call for more research into ways to prevent or mitigate these risks, proposing several as a starting point.