<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Output Handling on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/output-handling/</link><description>Recent content in Output Handling 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/tags/output-handling/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></channel></rss>