TechFlow News, July 11, according to CoinDesk, the Ethereum Foundation recently disclosed that its security team used AI agents to test the software running on Ethereum validator nodes and successfully discovered a vulnerability that could be triggered remotely, causing node crashes. However, researchers emphasized that amidst the large volume of security reports generated by AI, manual review remains a key step in distinguishing real vulnerabilities from false positives.
Reportedly, the vulnerability discovered this time exists in the Ethereum network message propagation protocol gossipsub. Attackers can remotely trigger the node software into an abnormal computation state, causing the program to crash and shut down, taking the validator node offline until the operator manually restarts it. The vulnerability has been fixed and registered under the number "CVE-2026-34219".
Nikos Baxevanis, a member of the Ethereum Foundation Protocol Security Team, stated that what was truly surprising about this incident was not the AI's ability to discover vulnerabilities, but rather the significant time the team spent distinguishing which vulnerabilities actually existed and which were just seemingly credible "hallucinations".
