<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Prompt Injection on Bruce on AI Engineering</title><link>http://www.heyuan110.com/tags/prompt-injection/</link><description>Recent content in Prompt Injection on Bruce on AI Engineering</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 24 Feb 2026 08:30:00 +0800</lastBuildDate><atom:link href="http://www.heyuan110.com/tags/prompt-injection/index.xml" rel="self" type="application/rss+xml"/><item><title>Stanford CS146S Deep Dive (4): Secure Vibe Coding — AI Code Security Guide</title><link>http://www.heyuan110.com/posts/ai/2026-02-24-secure-vibe-coding/</link><pubDate>Tue, 24 Feb 2026 08:30:00 +0800</pubDate><guid>http://www.heyuan110.com/posts/ai/2026-02-24-secure-vibe-coding/</guid><description>&lt;blockquote&gt;
&lt;p&gt;This is Part 4 of the &amp;ldquo;Stanford Vibe Coding Course Deep Dive&amp;rdquo; series. See the series navigation at the end of this article.&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;Weeks 6 and 7 of CS146S are the most spine-chilling weeks of the entire course.&lt;/p&gt;
&lt;p&gt;Week 6 covers security: when AI writes your code, who ensures it&amp;rsquo;s not vulnerable to attacks? Even scarier — what happens when the AI itself becomes the attack surface?&lt;/p&gt;
&lt;p&gt;Week 7 covers review: how much can we actually trust AI-generated code?&lt;/p&gt;</description></item></channel></rss>