Guide-linked quiz · Medium Level

Indirect Prompt Injection Quiz

Recognize attacks carried by untrusted content and apply layered controls around data flow, tools, and consequential actions.

Related guide pathsIndirect Prompt Injection
Question 1 of 8

What makes a prompt injection indirect?

Preview every question8 questions

Answers and explanations appear as you take the quiz.

  1. What makes a prompt injection indirect?
    • The user types the instruction directly into chat
    • The model receives no text
    • The adversarial instruction arrives inside content the assistant is asked to process
    • The instruction is part of the system prompt
  2. Which content could carry an indirect prompt injection?
    • A webpage, email, uploaded file, or retrieved document
    • Only a developer instruction
    • Only a model’s weights
    • A hardware temperature reading
  3. What can an indirect injection try to cause an agent to do?
    • Improve hardware throughput
    • Change the user’s password without access
    • Alter a file format automatically
    • Change behavior or misuse a connected tool, including exposing data
  4. Why does tool access raise the risk of prompt injection?
    • Tools make prompts deterministic
    • A manipulated response may trigger actions or data sharing beyond the text answer
    • Tools remove untrusted content
    • Tool calls cannot have side effects
  5. Which is a defense-in-depth measure?
    • Rely only on a prompt saying “ignore attacks”
    • Give every agent access to all data
    • Restrict tool permissions and validate arguments outside the model
    • Remove action confirmations
  6. Why use structured outputs for data extracted from an untrusted document?
    • They prove the document is trustworthy
    • They can limit free-form data flow and make fields easier to validate
    • They prevent all attacks automatically
    • They grant the model more permissions
  7. Does a model’s refusal behavior alone make a connected workflow secure?
    • No; authorization and tool controls should be enforced outside the model too
    • Yes, for every model and attack
    • Yes, if the prompt is long
    • No, because models cannot refuse
  8. What should a user review before confirming a consequential agent action?
    • Only the agent’s tone
    • Only the number of tools called
    • Nothing if the content came from a webpage
    • The exact action, destination, and information being shared

Keep testing yourself

More quizzes picked for your level.

View all quizzes