Lab 03: Public Enemy #1 — Direct and Indirect Prompt Injection
Evasion attacks via Typoglycemia, Unicode Smuggling, indirect injection in documents, and remediation with semantic validators and CI/CD tests.
Key Lab Topics
- Inyección Indirecta
- Unicode Smuggling
- Filtros de Entrada/Salida
- CI/CD Red Teaming
Prerequisites
- Python 3.10+
- Google GenAI API Key
Resources & Architecture Guide
This hands-on lab runs in a Jupyter Notebook (lab-03-inyeccion-prompts.ipynb) and includes a comprehensive architectural guide: