<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Codex-Security on SoloSoft</title><link>https://www.solosoft.dev/tags/codex-security/</link><description>Recent content in Codex-Security on SoloSoft</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 13 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.solosoft.dev/tags/codex-security/index.xml" rel="self" type="application/rss+xml"/><item><title>Codex Security Ships a 2,737-Case Accuracy Benchmark and Publishes No Score: 22,234 Semgrep Alerts Bucketed Into 2,737 Labels, 29.4% of the Evidence Is Vendored Code, and a Cost-Stopped Scan Is Sealed as Completed</title><link>https://www.solosoft.dev/post/codex-security-benchmark-published-no-score/</link><pubDate>Fri, 13 Nov 2026 00:00:00 +0000</pubDate><guid>https://www.solosoft.dev/post/codex-security-benchmark-published-no-score/</guid><description>&lt;p&gt;OpenAI&amp;rsquo;s Codex Security is the most adopted AI security scanner on npm: 785,567 downloads in the last 30 days, 27,360 of them on 11 November alone. The repository has 12,416 stars, 978 forks, 87 contributors, 1,989 commits and 55 releases since July.&lt;/p&gt;
&lt;p&gt;It also ships the most carefully specified accuracy harness I have seen in this category. Two thousand seven hundred and thirty-seven labelled cases, pinned to an exact upstream commit and verified by SHA-256. Twenty-one derived metrics with formulas written out one by one. A representative sampling scheme with inverse-probability weights. A documented label boundary that keeps ground truth out of the model&amp;rsquo;s working directory.&lt;/p&gt;</description></item></channel></rss>