quiz bu lëkkale ak tegtal · Dëgër Niveau

Leaking bu gaaw ak sistem bu gaaw ci génne quiz

Dafay saytu ni prompt leaking di doxee, naka lay wuute ak injection prompt, ak lu tax app yu wóor yi di denc sekkere ak doolel ci biti sistem bi.

Laaj 1 de 8

Lu tax mënu ñu garanti ni sistem bi dina nekk kumpa?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lu tax mënu ñu garanti ni sistem bi dina nekk kumpa?
    • System prompts are stored on public servers
    • The model reads it as ordinary text in its context, and keeping it private is only a learned tendency
    • All APIs publish system prompts automatically
    • System prompts are deleted after each message
  2. Lan moo wuutale senn bu gaaw ak pikiir bu gaaw?
    • Dañuy nuru
    • Leaking is about extracting hidden content, while injection is about making the model follow the attacker's instructions
    • Injection only affects images
    • Leaking only happens with open-source models
  3. Lan lañu wane ci sacc bu siiw bi tuddu Bing Chat ci weeru fewriye 2023?
    • Microsoft's source code
    • User passwords
    • Instructions including the internal codename Sydney
    • Done yiñ tàggat ci model bi
  4. Ban gis-gis la tegtal bi wax ni mooy anam wi gëna kawe ngir jëfandikoo caabi API bi app bi soxla?
    • Put it in the system prompt with a note saying 'keep this secret'
    • Encode it in base64 inside the prompt
    • Keep it in server-side code or a secrets manager and give the model scoped tools
    • Split it across several messages
  5. Lan moo waral ay filtre yu yomb te mënu ñu taxawal senn?
    • Filters slow the model too much to be used
    • Attackers can ask for the prompt paraphrased, translated or extracted a piece at a time
    • Filters only work on images
    • Output filters block all responses
  6. What is the purpose of placing a canary string in a system prompt?
    • To make the model answer faster
    • To detect in logs when the prompt has been leaked
    • To encrypt the prompt
    • To prevent all injection attacks
  7. A support bot's refund limit is written in its prompt and also enforced in the backend. What happens if the prompt leaks?
    • Users can now issue unlimited refunds
    • The rule becomes known but cannot be bypassed because the backend still enforces it
    • The bot shuts down
    • The refund limit is automatically deleted
  8. Which document listed system prompt leakage as its own risk in its 2025 edition?
    • The OWASP Top 10 for LLM Applications
    • The GDPR
    • The HTTP specification
    • The Unicode standard