Guide-yakabatana mibvunzo · Zvakaoma Nhanho

Kurumidza Leaking uye System Prompt Kubvisa Quiz

Inoedza kuti kudonha kunoshanda sei nekukurumidza, kuti kunosiyana sei nekukasira jekiseni, uye nei maapplication akachengeteka achichengeta zvakavanzika uye kuteedzera kunze kwehurongwa hwekukurumidza.

Nzira dzekutungamira dzinoenderanaKurumidza Kudonhedza Uye System Kurumidza Kubvisa
Mubvunzo 1 ye 8

Sei system isingagone kuvimbiswa kugara yakavanzika?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Sei system isingagone kuvimbiswa kugara yakavanzika?
    • 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. Kukurumidza kubuda kunosiyana sei nejekiseni rekukurumidza?
    • Vakafanana chaizvo
    • 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. Chii chakaburitswa mune inozivikanwa Bing Chat leak muna Kukadzi 2023?
    • Microsoft's source code
    • User passwords
    • Instructions including the internal codename Sydney
    • Data yekudzidzisa yemuenzaniso
  4. Ndeipi nzira iyo gwara rinoti ndiyo yakachengeteka nzira yekubata API kiyi inodiwa neapp?
    • 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. Sei masefa ari nyore anobuda achitadza kumisa kubuda?
    • 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
    • Iye GDPR
    • The HTTP specification
    • The Unicode standard