Ethereum Foundation uses AI agents for red team testing of the ETH network and discovers real vulnerabilities

Odaily reported that researchers from the Ethereum Foundation Protocol Security team said in a blog post on Thursday that they have deployed a series of AI agents to test the software relied upon by Ethereum, 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 the libp2p gossipsub 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 their applicability 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 scope than manual review. However, it requires researchers to exercise more careful judgment when evaluating a large number of seemingly credible conclusions. (Decrypt)