Discussion on "I couldn't find an AI agent for AppSec audits, so I built one and benchmarked it on real CVEs"

vlfd · 2026-11-12T13:11:51.693Z

An open-source tool that turns Claude Code into a repeatable AppSec auditor, measured on CWE-Bench-Java: 57% recall, about $0.22 per run.

Discussion on "I couldn't find an AI agent for AppSec audits, so I built one and benchmarked it on real CVEs" | Hashnode

I couldn't find an AI agent for AppSec audits, so I built one and benchmarked it on real CVEs