According to Ethereum Foundation's Protocol Security team, on Thursday, AI agents were deployed to test software that Ethereum relies on and identified a remote-triggerable panic vulnerability in libp2p gossipsub, a peer-to-peer layer used by Ethereum consensus clients. The vulnerability was disclosed as CVE-2026-34219 and has already been patched.
The AI agents were organized into specialized roles—reconnaissance, discovery, gap-filling, and validation—to identify potential attack paths, reproduce failures, and verify their applicability to production code. The Foundation stated that AI augments rather than replaces security researchers, enabling teams to cover significantly broader scope than manual review alone.