Prompt-Engineering on Elliot Belthttps://felixbillieres.github.io/tags/prompt-engineering/Recent content in Prompt-Engineering on Elliot BeltHugo -- gohugo.ioenfelix.billieres@ecole2600.com (Elliot Belt)felix.billieres@ecole2600.com (Elliot Belt)© 2026 Elliot BeltThu, 07 May 2026 00:00:00 +0000Prompting for Security Research: How to Build Prompts That Actually Find Vulnerabilitieshttps://felixbillieres.github.io/posts/prompting-for-cybersecurity-2026/Thu, 07 May 2026 00:00:00 +0000felix.billieres@ecole2600.com (Elliot Belt)https://felixbillieres.github.io/posts/prompting-for-cybersecurity-2026/Most people use LLMs for security wrong. They ask ‘find all bugs’ and get noise. This article breaks down the empirical research behind what actually works: structured prompting, adversarial self-verification, CWE-specialized chains, context engineering, and the full composite prompt template that gets you from noise to actionable findings. With numbers.