Coming Soon / Demo StageFoundationalEst. 45 mins

Prompt-Injection Playground (AI App Security)

Explore prompt injection, system prompt extraction, and input/output guardrails in LLM-powered applications.

AI SafetyPrompt InjectionLLM GuardrailsOWASP Top 10 for LLM

Authorized Testing & Ethical Guardrails

Always follow legal authorization boundaries. Only conduct security assessments on systems you own or have received explicit, written authorization to test. This curriculum is strictly defensive and educational.

Learning Goals & Competencies

Understand direct and indirect prompt injection vectors.

Test defensive prompt wrapping and delimiter isolation.

Implement structured output validation and safety classifiers.

Recommended Prerequisites

Basic Python or JavaScript understanding
Familiarity with API calls

Sandbox Environment Status

This lab is currently in syllabus design. Live container environments are not yet deployed.

Want early access when the browser container for this module opens?Notify Me When Live →