https://jameslee177.github.io/Recent content on James Lee | Security NotesHugoen-usFri, 30 Oct 2026 16:00:00 +0800https://jameslee177.github.io/posts/prompt-injection-part-2/Fri, 30 Oct 2026 16:00:00 +0800https://jameslee177.github.io/posts/prompt-injection-part-2/A well-written system prompt can stop simple attacks, but it is not a security boundary.https://jameslee177.github.io/posts/prompt-injection-part-1/Fri, 30 Oct 2026 00:00:00 +0000https://jameslee177.github.io/posts/prompt-injection-part-1/Before we can break an AI application, we need to understand the controls that shape its behavior.https://jameslee177.github.io/about/Mon, 01 Jan 0001 00:00:00 +0000https://jameslee177.github.io/about/<p>Hi, I&rsquo;m <strong>James Lee</strong> — a security engineer based in Singapore with more than 20 years of experience in cybersecurity.</p> <p>Over the years, I&rsquo;ve worked across a wide range of security domains, from network and access security to application protection. Today, much of my focus is on securing AI applications and infrastructure, while still working hands-on with the security technologies that surround them.</p> <h2 id="what-i-work-on">What I work on</h2> <ul> <li><strong>AI Security</strong>: prompt injection, jailbreaks, guardrails, AI runtime firewalls, and agent/MCP security</li> <li><strong>Application Security</strong>: WAF, API security, and bot defense</li> <li><strong>Identity &amp; Access</strong>: OAuth 2.0, OpenID Connect (OIDC), and SAML-based authentication and federation</li> <li><strong>Network &amp; Secure Access</strong>: Secure Web Gateways (SWG) and VPN</li> <li><strong>Threat Defense</strong>: malware based attacks detection and protection</li> </ul> <h2 id="what-i-write-about">What I write about</h2> <p>Most posts here focus on AI security, but I also write about application security and the broader cybersecurity topics above. Many of them come from experiments in my own lab: I like to break things first, then work out how to defend them.</p>