TMAI practice · Module 4

AI Threat Modelling — 10 questions. Choose the BEST answer.

You can answer as a guest, but you'll need a free account to see your score and save it. Sign up · Sign in
Question 1 Question 1 · M4
Which two principles underpin the OWASP Top 10 for Agentic Applications?
Question 2 Question 2 · M4
What is the root cause of prompt injection?
Question 3 Question 3 · M4
Which question finds most serious AI agent threats?
Question 4 Question 4 · M4
In a RAG assistant, where must the permission filter be applied?
Question 5 Question 5 · M4
Which framework is BEST for planning AI red-team attack paths?
Question 6 Question 6 · M4
Which is the BEST general principle for securing LLM applications?
Question 7 Question 7 · M4
Why should an inference API return only coarse outcomes instead of precise scores?
Question 8 Question 8 · M4
Injected content makes an assistant output a Markdown image with data in its URL, which the browser fetches. Which control breaks this most reliably?
Question 9 Question 9 · M4
In the OWASP Top 10 for LLM Applications 2026, what is LLM03?
Question 10 Question 10 · M4
An ML model's training data is updated monthly with disputed cases labelled by reviewers, unchecked. Which control MOST directly reduces poisoning?