LLM security

Free hands-on labs for prompt injection and LLM security training, with real models, a context trace view of assembled prompts, and a multi-level Gauntlet challenge.

Open-source runtime guardrails for AI agents that scans for prompt-injection weaknesses and blocks unsafe tool calls at execution time with a decorator.

A Python package that adds Conduct Guard as a LiteLLM guardrail to enforce runtime policy on LLM calls. The page explains install, proxy wiring, verdict behavior, session tracking, fail modes, and configuration options.