AI firm Anthropic says its latest tests showed AI agents autonomously hacking top blockchains and draining simulated funds, signaling that automated exploits may now threaten blockchains like Ethereum (CRYPTO: ETH), XRP (CRYPTO: XRP) and Solana (CRYPTO: SOL) at scale.
AI Agents Execute Realistic Exploits Across Ethereum, BNB Chain And Base
A test environment showed AI models, including Claude Opus 4.5 and Claude Sonnet 4.5, exploiting 17 of 34 smart contracts deployed after March 2025.
The models drained $4.5 million in simulated funds, according to Anthropic.
The company expanded the experiment to 405 previously exploited contracts across Ethereum, BNB Smart Chain (CRYPTO: BNB), and Base.
The result: AI agents executed 207 profitable attacks, generating $550 million in simulated revenue.
The report said these models replicated real-world attacker behavior by identifying bugs, generating full exploit scripts and sequencing transactions to drain liquidity pools.
Anthropic noted that the tests demonstrate how AI agents now automate tasks historically performed by skilled human hackers.
GPT-5 And Sonnet Models Discover Zero-Day Bugs In New Contracts
Researchers from the ML Alignment & Theory Scholars Program and the Anthropic Fellows Program also tasked GPT-5 and Sonnet 4.5 with scanning 2,849 recently deployed contracts that showed no signs of compromise, according to CoinDesk.
The models uncovered two previously unknown vulnerabilities that allowed unauthorized withdrawals and balance manipulation.
The exploits produced $3,694 in simulated gains at a total compute cost of $3,476 — the average cost of a single exploit run was $1.22.
According to Anthropic, declining model costs will make automated scanning and exploitation more economically attractive for attackers.
Exploitation Capability Growing Faster Than Defenses
More than half of the blockchain attacks recorded in 2025 could have been executed autonomously by current-generation AI agents.
The company warned that exploit revenue doubled every 1.3 months last year as models improved and operational costs declined.
The firm said attackers can now probe any contract interacting with valuable assets, including authentication libraries, logging tools, or long-neglected API endpoints.
It added that the same reasoning used to exploit decentralized finance protocols could apply to traditional software and infrastructure supporting digital asset markets.
AI Could Also Strengthen Smart Contract Security
Despite the risks, Anthropic said the same agents capable of identifying and exploiting flaws can be adapted to detect and patch vulnerabilities before deployment.
The company plans to open-source its SCONE-bench dataset to help developers benchmark and harden smart contracts.
The findings should shift expectations among blockchain builders, noting that "now is the time to adopt AI for defense," Anthropic concluded.
Read Next:
Image: Shutterstock
© 2025 Benzinga.com. Benzinga does not provide investment advice. All rights reserved.
