Ethereum Foundation Taps AI to Find Bugs Before Hackers Do

The Ethereum Foundation is using AI agents to test its own code for vulnerabilities in the Ethereum network.

In a blog post, researchers on the Protocol Security team said they deployed AI agents against the software Ethereum relies on, hunting for weaknesses in cryptographic systems, protocol code, and smart contracts.

The agents helped uncover a peer-to-peer software vulnerability that was later disclosed as CVE-2026-34219. This bug allowed for a remotely triggered panic in libp2p's gossipsub, part of the peer-to-peer layer used by Ethereum consensus clients.

AI-assisted audits have already surfaced bugs in blockchain projects, including Zcash. In May, security researcher Taylor Hornby used Anthropic’s Claude Opus 4.8 to find a critical vulnerability in Zcash's Orchard privacy pool that could have allowed an attacker to create counterfeit ZEC without an obvious on-chain trace.

The Ethereum Foundation's experiment brings the technology in-house, using AI agents to test its own code.