<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Application Security on AI VOID</title><link>https://ai-blog.noorshomelab.dev/categories/application-security/</link><description>Recent content in Application Security on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 20 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/categories/application-security/index.xml" rel="self" type="application/rss+xml"/><item><title>Agentic AI Security: Tool Misuse &amp;amp; Insecure Output Handling</title><link>https://ai-blog.noorshomelab.dev/ai-security-guide-2026/agentic-ai-tool-misuse/</link><pubDate>Fri, 20 Mar 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/ai-security-guide-2026/agentic-ai-tool-misuse/</guid><description>&lt;h2 id="introduction-to-agentic-ai-security-tools-and-outputs"&gt;Introduction to Agentic AI Security: Tools and Outputs&lt;/h2&gt;
&lt;p&gt;Welcome back, future AI security experts! In our previous chapters, we delved into the intricacies of prompt injection and jailbreak attacks, learning how attackers try to manipulate Large Language Models (LLMs) directly. We saw that securing the prompt interface is crucial, but it&amp;rsquo;s just one piece of the puzzle.&lt;/p&gt;
&lt;p&gt;Today, we&amp;rsquo;re leveling up our understanding to &lt;strong&gt;agentic AI systems&lt;/strong&gt;. Imagine an LLM not just as a chatbot, but as a clever assistant that can &lt;em&gt;use tools&lt;/em&gt; – like searching the web, running code, or interacting with other applications. This capability unlocks incredible power but also introduces entirely new security challenges. How do we ensure our AI agent uses its tools responsibly? What happens if an attacker makes the agent use a tool in a malicious way? And once the agent generates an output, how do we ensure that output isn&amp;rsquo;t harmful or exploitable by other systems?&lt;/p&gt;</description></item><item><title>Building Secure AI Applications: A Defense-in-Depth Approach</title><link>https://ai-blog.noorshomelab.dev/ai-security-guide-2026/secure-ai-application-design/</link><pubDate>Fri, 20 Mar 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/ai-security-guide-2026/secure-ai-application-design/</guid><description>&lt;h2 id="introduction"&gt;Introduction&lt;/h2&gt;
&lt;p&gt;Welcome back, future AI security champions! In our previous chapters, we delved into specific vulnerabilities like prompt injection, jailbreaks, data poisoning, and tool misuse. We learned to identify these threats and even explored some initial mitigation techniques. But how do we tie all of this together into a cohesive, robust security strategy for an entire AI application?&lt;/p&gt;
&lt;p&gt;That&amp;rsquo;s precisely what we&amp;rsquo;ll tackle in this chapter: &lt;strong&gt;Building Secure AI Applications with a Defense-in-Depth Approach&lt;/strong&gt;. We&amp;rsquo;ll move beyond individual fixes to understanding how to design AI systems that are inherently more resilient against a wide array of attacks. Our goal is to equip you with the knowledge to architect AI applications that are not just functional, but truly &lt;em&gt;production-ready&lt;/em&gt; – meaning they can withstand sophisticated threats in the real world.&lt;/p&gt;</description></item></channel></rss>