Security
3 articles about Security from damore.ai: private AI, automation, and Open WebUI guides for small businesses.
Preventing Prompt Injection in Local LLMs: A Working Defense
How to detect and block prompt injection attacks in self-hosted LLM deployments using a dedicated classifier model in Open WebUI — with a nine-category attack taxonomy, violation logging, and lockout.
Implementing ClamAV File Scanning in Open WebUI
Step-by-step guide to adding real-time antivirus scanning to Open WebUI file uploads with ClamAV: Docker setup, filter installation, violation logging, and automatic user lockout.
Three Layers of Safety: How We Protect Every Conversation
Every conversation on the Cross & Faith AI platform passes through three independent safety filters — prompt injection protection, content safety, and policy enforcement.
Let's find your first three wins
A free 20-minute call. Bring the workflow that annoys you most. I will tell you honestly whether AI fixes it and what the first stage would cost.
Prefer to write first? Send a short inquiry and I reply within one business day.