Our Blog

Running the Full Security Pipeline on Bloxchain Protocol
September 17, 2026
Nethermind Security audited Particle CS's Bloxchain Protocol, an EVM security framework, via AuditAgent, AgentArena, and a full manual audit.

Speed, Cost, and Ecosystem Coverage: The Next Constraints in AI Security Analysis
April 22, 2026
The 2026 constraints on AI security tooling are how fast analysis runs, what it costs at scale, and how much it covers.

Recall Is Not Enough: False Positives and the Limits of Benchmarking
April 16, 2026
Recall says what a tool finds, not what it costs. AuditAgent's validation cut false positives by 75%, from 3,230 to 798. Why benchmarks need precision too.

AuditAgent on EVMBench: 40 Repositories, 120 Vulnerabilities, No Repos Skipped
April 7, 2026
AuditAgent detected 80 of 120 high-severity vulnerabilities on EVMBench. 40 repositories, run in order, no repos skipped. Full results and methodology.

Using AI-assisted security analysis on the CMTAT: Case study of how CMTA and UBS have used Nethermind's AuditAgent on CMTAT contracts
January 27, 2026
How the UBS team and CMTAT developers ran Nethermind's AuditAgent on 75 contracts of the CMTAT Solidity token standard before the v3.1.0 release.

What LUKSO Learned Running AI-Assisted Security Analysis on Their Hyperlane Bridge Contracts
December 1, 2025
How LUKSO used AuditAgent as a security AI copilot on their HypLSP7 and HypLSP8 Hyperlane bridge contracts before engaging external auditors.

How Nethermind Security Uses AuditAgent Alongside Manual Audits
Last Updated: 20 September 2025
Nethermind Security ran AuditAgent after 29 manual audits to see what was missed: valid issues in 62% of projects, and 30% of all auditor findings matched.
