Ethereum Foundation Uses AI Agents to Red Team the ETH Network and Discover Real Vulnerabilities

Odaily reported that the Ethereum Foundation Protocol Security research team stated in a blog post on Thursday that it has deployed a series of AI agents to test the software Ethereum relies on, searching for vulnerabilities in encryption systems, protocol code, and smart contracts. The vulnerabilities discovered by the AI agents include a remotely triggerable panic issue in libp2p gossipsub, the peer-to-peer layer used by Ethereum consensus clients. The issue has been fixed and disclosed on GitHub as CVE-2026-34219. Researchers stated that the AI agents are organized into specialized roles such as reconnaissance, search, patching, and verification, used to find potential attack paths, reproduce faults, and verify whether they apply to production code. The Ethereum Foundation stated that AI has not replaced security researchers but has changed the way they work, enabling the team to cover far more ground than manual review alone. However, it requires researchers to exercise more careful judgment over a large number of seemingly plausible conclusions. (Decrypt)