引導式測驗 · 硬 等級
提示洩漏和系統提示提取測驗
測試提示洩漏的工作原理、它與提示注入有何不同,以及為什麼安全應用程式在系統提示之外保守秘密和執行。
問題 1 的 8
Why can't a system prompt be guaranteed to stay secret?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- Why can't a system prompt be guaranteed to stay secret?
- 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
- How does prompt leaking differ from prompt injection?
- 它們是完全相同的東西
- 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
- What was revealed in the well-known Bing Chat leak in February 2023?
- Microsoft's source code
- User passwords
- Instructions including the internal codename Sydney
- 模型的訓練數據
- Which approach does the guide say is the safest way to handle an API key the app needs?
- 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
- Why can simple output filters fail to stop a leak?
- 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
- 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
- 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
- Which document listed system prompt leakage as its own risk in its 2025 edition?
- The OWASP Top 10 for LLM Applications
- 一般資料保護條例
- The HTTP specification
- The Unicode standard