Testing the Untestable: Turning OWASP AI/LLM Risks into Practical QA Checks

AI and LLM features are now entering products faster than most teams can test them. That speed creates a new quality gap: traditional test automation verifies APIs and UI flows, but it often misses prompt injection, data leakage, unsafe output, hallucinations, agent misuse and model behavior drift. This talk shows how testers can translate OWASP AI/LLM risk categories into a practical testing approach that fits real QA pipelines.

Attendees will learn how to think about AI systems as testable software components across the application, model, infrastructure and data layers. The session will demonstrate how to design test cases for prompt injection, indirect prompt injection, sensitive-data exposure, output safety and agentic behavior limits, then convert those into repeatable checks for regression, CI/CD, and release gates.

The focus is deliberately testing-first: what a QA engineer can observe, assert, automate and report. By the end, participants will leave with a tester's checklist for AI features, a simple risk-based framework for prioritizing test effort and ideas for integrating AI security verification into everyday quality engineering practice.