Bug hunting with LLMs works. The security concept of Glaswing can be applied in open source / with open-weight models. The model is exchangeable. The logic isn't.
Marius Ciepluch
HH
8 posts
I am sure you also received a cold sales call or two. AI pentesting as a Service. Is this real or hype? In the following, I test 5 different open source AI pentest tools and how they perform against a purposely vulnerable Java Web App. While 2025 has been a
💡If you are interested in a high-level executive summary about the pillars of Zero Trust, read this article. Simplicity is the most difficult thing to secure in this world; it is the last limit of experience and the last effort of genius. George Sand Summary What problem does Zero
Projects
AI Skills for strategic foresight, intelligence analysis and investigation theory
May 27, 2026
AI Skills for decision intelligence and visualization.
Social network intelligence: X trend analysis
May 27, 2026
Trend analysis via social-media open source intelligence based on Likes. Use the X algorithm for your awareness.
Nvim Simple to reduce the AI vs. human context gap when you take over the work
February 11, 2026
Nvim Simple is my version of a different Nvim usage. It's optimized for taking over when the AI agents fail.
Terminal for Automation with Quant Models
August 29, 2025
Quant terminal for quantitative financial models. No AI involved. Math and Python with thorough testing for hypothesis building.
RAGflow MCP server for Claude Desktop and Agentic Coding
June 10, 2025
RAGflow is a knowledge base for your books, reports, documents, and tables. It uses custom (local) models and established (remote) LLMs to interact with AI agents. I wrote an MCP server for it, that works with Claude, opencode and other clients