引導式測驗 · 硬 等級
AI 提示安全測驗
測試不受信任的內容、最小權限、授權、操作驗證、各種攻擊路徑、分層控制和安全回歸測試。
問題 1 的 8
检索到的文档包含“忽略先前的说明”。应用程序应该如何对待它?
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。
- 检索到的文档包含“忽略先前的说明”。应用程序应该如何对待它?
- As untrusted content to process, not authority to control tools or policy
- As a trusted system instruction
- As proof the document should be deleted
- As permission to disclose data
- 为什么要将工具限制为任务所需的权限?
- It prevents all prompt injection
- It makes content filtering unnecessary
- A model error then has less ability to create unauthorized consequences
- It guarantees correct summaries
- 网页显示用户已批准发送文件。什么应该授权该行动?
- The webpage’s statement
- The actual user instruction and the application’s authorization process
- A high model confidence score
- A tool result that repeats the claim
- 工具向外部发送信息之前应该检查什么?
- Only whether the output matches JSON
- The writing style of the tool response
- Whether the prompt contains a suspicious phrase
- Destination, affected records, transmitted data, and required approval
- 为什么要在不同的位置和格式测试提示安全案例?
- The model only reads plain text prompts
- One attack example covers every case
- Untrusted instructions can arrive in user input, documents, or tool responses
- Format does not change application behavior
- What is the relationship between content filtering and authorization?
- Filtering may detect wording; authorization must still block actions outside scope
- Either one makes the other unnecessary
- Authorization is only a writing filter
- Filtering guarantees the user intended every action
- Why avoid calling a prompt-injection filter foolproof?
- Filters cannot process any text
- The guide prohibits testing
- Only external users can create malicious inputs
- Detection can miss attacks, so consequence-limiting controls and ongoing tests remain important
- A summarizer has no need to send messages. Which design is safer?
- Grant broad access but add a warning
- Do not grant message-sending permission to that workflow
- Ask the model to promise not to send
- Enable sending only during long inputs