<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai-Generated-Code on CuraSec</title><link>https://curasec.metacog.co.kr/tags/ai-generated-code/</link><description>Recent content in Ai-Generated-Code on CuraSec</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 21 Sep 2026 18:11:48 +0000</lastBuildDate><atom:link href="https://curasec.metacog.co.kr/tags/ai-generated-code/index.xml" rel="self" type="application/rss+xml"/><item><title>Study: Developers Often Miss Vulnerabilities in AI-Generated Code</title><link>https://curasec.metacog.co.kr/insights/2026-09-21-don-t-trust-but-don-t-verify-developers-attention-to-securit/</link><pubDate>Mon, 21 Sep 2026 18:11:48 +0000</pubDate><guid>https://curasec.metacog.co.kr/insights/2026-09-21-don-t-trust-but-don-t-verify-developers-attention-to-securit/</guid><description>&lt;ul>
&lt;li>&lt;strong>Engineer — Learn:&lt;/strong> Research finds developers systematically under-scrutinize AI-generated code for vulnerabilities — useful context for how engineers should treat AI autocomplete and chat output, but no patch or configuration change is required today.&lt;/li>
&lt;li>&lt;strong>SOC/IR — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>Leader — Learn:&lt;/strong> Provides empirical grounding for AI coding-tool governance conversations — useful data when building policy around AI-assisted development, but no immediate deadline or vendor exposure to act on.&lt;/li>
&lt;/ul></description></item></channel></rss>