The Missing `bandit` for AI Agents: How I Built a Static Analyzer for Prompt Injection

If you’re building LLM agents with LangGraph or the OpenAI Agents SDK, your architecture might already be vulnerable — and no runtime tool will catch it before you ship.

The Problem Nobody Is Talking About

Everyone is building AI agents. Everyone is worried about prompt injection. But almost all the tooling to prevent it works at runtime — it inspects prompts as they flow through the system and tries to block malicious content.