https://blog.my-techcore.com/en/posts/Recent content in Posts on GuanLin's Latent SpaceHugo -- gohugo.ioen© 2026 GuanLin's Latent Space. All rights reserved.Thu, 04 Jun 2026 10:00:00 +0800https://blog.my-techcore.com/en/posts/owasp-agentic-ai-top10/Thu, 04 Jun 2026 10:00:00 +0800https://blog.my-techcore.com/en/posts/owasp-agentic-ai-top10/<div class="lead text-neutral-500 dark:text-neutral-400 !mb-9 text-xl"> We used to protect &ldquo;Model Output.&rdquo; Now we must protect &ldquo;Autonomous Behavior.&rdquo; When AI can plan on its own, invoke its own tools, and execute its own tasks, the traditional LLM security model is no longer sufficient. </div> <hr> <h2 class="relative group">A New Security Crisis: AI Is No Longer Just Answering Questions <div id="a-new-security-crisis-ai-is-no-longer-just-answering-questions" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#a-new-security-crisis-ai-is-no-longer-just-answering-questions" aria-label="Anchor">#</a> </span> </h2> <p>If you still think of large language models (LLMs) as &ldquo;chatbots that answer questions,&rdquo; you may be underestimating the systemic risk of the next two years.</p>