Security Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of Public GitHub Repositories · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2510.26103/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:27:26 GMTSecurity Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of Public GitHub Repositories — HN submissionhttps://news.ycombinator.com/item?id=46820686urn:hackerpapers:submission:2510.26103:46820686Fri, 30 Jan 2026 04:58:43 GMT<p>Show HN: I made a dev tool that helps vibecoders to AVOID security issues</p><p>The first time I have heard about the vibecoding I could not believe that peeps without the technical background dare to release web apps and other type of software within the week of using such stuff like cursor, claude code and later lovable, bolt.new and etc. I saw some of the projects like that and despite them being somewhat functional - I could feel that security was not the strongest side of these pieces of software. As it turned out I was not hallucinating about the existance of the said security problem - lots of papers were published in this regard. For example, just last quarter 2…</p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2510.26103/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CR