<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Prompt-Injection on Albert G&#39;s Blog</title>
    <link>https://blog.alberyt.xyz/tags/prompt-injection/</link>
    <description>Recent content in Prompt-Injection on Albert G&#39;s Blog</description>
    <generator>Hugo -- 0.161.1</generator>
    <language>en</language>
    <lastBuildDate>Sat, 14 Jun 2025 12:13:48 +0000</lastBuildDate>
    <atom:link href="https://blog.alberyt.xyz/tags/prompt-injection/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>How I Prompt-Injected ChatGPT to Leak Its Own Security Policy</title>
      <link>https://blog.alberyt.xyz/posts/prompt-injected-chatgpt-security-policy/</link>
      <pubDate>Sat, 14 Jun 2025 12:13:48 +0000</pubDate>
      <guid>https://blog.alberyt.xyz/posts/prompt-injected-chatgpt-security-policy/</guid>
      <description>Step-by-step walkthrough of a real prompt-injection that persuaded PromptEngineerGPT to hand over OpenAI&amp;#39;s internal security policy.</description>
    </item>
  </channel>
</rss>
