<?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 Nitin Kumar Singh</title><link>https://nitinksingh.com/tags/prompt-injection/</link><description>Recent content in Prompt-Injection on Nitin Kumar Singh</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Nitin Kumar Singh. All rights reserved.</copyright><lastBuildDate>Sun, 24 May 2026 10:00:00 +0530</lastBuildDate><atom:link href="https://nitinksingh.com/tags/prompt-injection/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Security: Prompt Injection, Jailbreaks, and Guardrails</title><link>https://nitinksingh.com/posts/ai-security-prompt-injection-jailbreaks-and-guardrails/</link><pubDate>Sun, 24 May 2026 10:00:00 +0530</pubDate><guid>https://nitinksingh.com/posts/ai-security-prompt-injection-jailbreaks-and-guardrails/</guid><description>&lt;p&gt;The OWASP LLM Top 10 exists because shipping an LLM to production without a security model is a new category of risk that the existing web application security playbook doesn&amp;rsquo;t fully cover. Prompt injection has held the #1 spot on that list since the first version was published, and it&amp;rsquo;s not there because researchers think it might be a problem someday. It&amp;rsquo;s been demonstrated against production systems at companies that knew what they were doing.&lt;/p&gt;</description></item></channel></rss>