# AI Agent Smart Contract Exploit Generation

arXiv: https://arxiv.org/abs/2507.05558 · HTML: https://mlsanity.com/paper/2507.05558/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 20 of 20)

- [Slither: A Static Analysis Framework For Smart Contracts](https://mlsanity.com/paper/1908.09878/) (2019)
- [Securify: Practical Security Analysis of Smart Contracts](https://mlsanity.com/paper/1806.01143/) (2018)
- [Do you still need a manual smart contract audit?](https://mlsanity.com/paper/2306.12338/) (2023)
- [ContractFuzzer: Fuzzing Smart Contracts for Vulnerability Detection](https://mlsanity.com/paper/1807.03932/) (2018)
- [SoK: Decentralized Finance (DeFi) Attacks](https://mlsanity.com/paper/2208.13035/) (2022)
- [Finding The Greedy, Prodigal, and Suicidal Contracts at Scale](https://mlsanity.com/paper/1802.06038/) (2018)
- [Exploring ChatGPT's Capabilities on Vulnerability Management](https://mlsanity.com/paper/2311.06530/) (2023)
- [Sereum: Protecting Existing Smart Contracts Against Re-Entrancy Attacks](https://mlsanity.com/paper/1812.05934/) (2018)
- [Blockchain Large Language Models](https://mlsanity.com/paper/2304.12749/) (2023)
- [Quantifying Blockchain Extractable Value: How dark is the forest?](https://mlsanity.com/paper/2101.05511/) (2021)
- [ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts](https://mlsanity.com/paper/2403.06838/) (2024)
- [Harvey: A Greybox Fuzzer for Smart Contracts](https://mlsanity.com/paper/1905.06944/) (2019)
- [High-Frequency Trading on Decentralized On-Chain Exchanges](https://mlsanity.com/paper/2009.14021/) (2020)
- [Attacking the DeFi Ecosystem with Flash Loans for Fun and Profit](https://mlsanity.com/paper/2003.03810/) (2020)
- [On the Just-In-Time Discovery of Profit-Generating Transactions in DeFi Protocols](https://mlsanity.com/paper/2103.02228/) (2021)
- [ItyFuzz: Snapshot-Based Fuzzer for Smart Contract](https://mlsanity.com/paper/2306.17135/) (2023)
- [EF/CF: High Performance Smart Contract Fuzzing for Exploit Generation](https://mlsanity.com/paper/2304.06341/) (2023)
- [Are We There Yet? Unraveling the State-of-the-Art Smart Contract Fuzzers](https://mlsanity.com/paper/2402.02973/) (2024)
- [Smart Contract Fuzzing Towards Profitable Vulnerabilities](https://mlsanity.com/paper/2501.08834/) (2025)
- [Generative Large Language Model usage in Smart Contract Vulnerability Detection](https://mlsanity.com/paper/2504.04685/) (2025)

## Built on by (most cited first, 9 of 9)

- [PoCo: Agentic Proof-of-Concept Exploit Generation for Smart Contracts](https://mlsanity.com/paper/2511.02780/) (2025)
- [Prompt to Pwn: Automated Exploit Generation for Smart Contracts](https://mlsanity.com/paper/2508.01371/) (2025)
- [Towards Optimal Agentic Architectures for Offensive Security Tasks](https://mlsanity.com/paper/2604.18718/) (2026)
- [TxRay: Agentic Postmortem of Live Blockchain Attacks](https://mlsanity.com/paper/2602.01317/) (2026)
- [Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization](https://mlsanity.com/paper/2603.26270/) (2026)
- [Crypto x AI, AI x Crypto: A Survey](https://mlsanity.com/paper/2606.13892/) (2026)
- [LLMs as verification oracles for Solidity](https://mlsanity.com/paper/2509.19153/) (2025)
- [Benchmarking Mythos-Linked Bug Rediscovery](https://mlsanity.com/paper/2605.17416/) (2026)
- [CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?](https://mlsanity.com/paper/2606.26216/) (2026)

## Abstract (arXiv)

Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with complex attacks, while human auditors are thorough but slow and don't scale. Large Language Models offer a promising middle ground, combining human-like reasoning with machine speed. Early studies show that simply prompting LLMs generates unverified vulnerability speculations with high false positive rates. To address this, we present A1, an agentic system that transforms any LLM into an end-to-end exploit generator. A1 provides agents with six domain-specific tools for autonomous vulnerability discovery, from understanding contract behavior to testing strategies on real blockchain states. All outputs are concretely validated through execution, ensuring only profitable proof-of-concept exploits are reported. We evaluate A1 across 36 real-world vulnerable contracts on Ethereum and Binance Smart Chain. A1 achieves a 63% success rate on the VERITE benchmark. Across all successful cases, A1 extracts up to 8.59 million per exploit and 9.33 million total. Using Monte Carlo analysis of historical attacks, we demonstrate that immediate vulnerability detection yields 86-89% success probability, dropping to 6-21% with week-long delays. Our economic analysis reveals a troubling asymmetry: attackers achieve profitability at 6,000 exploit values while defenders require 60,000 -- raising fundamental questions about whether AI agents inevitably favor exploitation over defense.