https://ku5e.com/tags/prompt-injection/Recent content in Prompt-Injection on ku5e | Cybersecurity PortfolioHugo -- 0.162.1en-usWed, 22 Apr 2026 19:22:00 +0000https://ku5e.com/blog/zero-click-prompt-injection-in-claude-s-chrome-extension-one-iframe-no-warning-everything-gone/Wed, 22 Apr 2026 19:22:00 +0000https://ku5e.com/blog/zero-click-prompt-injection-in-claude-s-chrome-extension-one-iframe-no-warning-everything-gone/ku5e.com blog article on the zero-click prompt injection vulnerability in Claude's official Chrome extension — patched in v1.0.41.https://ku5e.com/blog/your-background-ai-agent-will-read-whatever-you-download/Tue, 21 Apr 2026 20:13:00 +0000https://ku5e.com/blog/your-background-ai-agent-will-read-whatever-you-download/description: ku5e.com blog article on the attack surface created by background AI agents with computer use permissions — Codex, Perplexity Personal Computer, browser agents.https://ku5e.com/blog/193-applications-taught-me-that-hr-ai-agents-are-an-unmonitored-attack-surface/Mon, 13 Apr 2026 20:09:00 +0000https://ku5e.com/blog/193-applications-taught-me-that-hr-ai-agents-are-an-unmonitored-attack-surface/description: HR AI agents are running application screeners, confirmation senders, denial generators, and support chats. They read unstructured external input and route it into internal processes. That is an injection surface. Most companies did not buy them as security infrastructure.