Question 310
At Redfern Aviation, a supplier operations group is improving spare-part quotations while preparing a production promotion (SF-P19-02). The administrator observes that a case-summary prompt may contain personal contact information that must not be exposed beyond authorization. Any fix must ensure that supplier prices are never shown outside entitled teams. Which continuing control best prevents this issue from recurring?
Explanation
Correct Answer
The preventive control directly addresses repeat failures: Audit sensitive-field access and verify prompt inputs before release; require the check in the next release review at Redfern Aviation (SF-P19-02). It complements the corrective action, use the supported Salesforce Trust Layer protections and enforce source access rules, and protects the explicit condition that supplier prices are never shown outside entitled teams.
Incorrect Answers
This safeguard, “Maintain adversarial retrieval and instruction hierarchy tests; review it before expanding channel availability”, reduces a different source-defined risk: A retrieved knowledge article includes instructions telling the assistant to ignore the company policy. The correction must ensure that work order updates follow supported automation guardrails. That risk depends on: External content must not become trusted operational instruction merely because it is retrieved. The recurring problem here is a case-summary prompt may contain personal contact information that must not be exposed beyond authorization. The correction must ensure that supplier prices are never shown outside entitled teams. The originally selected control “Audit sensitive-field access and verify prompt inputs before release; review it as part of periodic access and quality reviews” is more specific because the Trust Layer supplies security and privacy safeguards but cannot replace data permissions.
This safeguard, “Run negative record-access tests before expanding agent privileges; review it and retest after dependent metadata changes”, reduces a different source-defined risk: A manager assumes Trust Layer usage automatically grants agents unrestricted access to customer records. The correction must ensure that employee identity is verified before accessing private tickets. That risk depends on: Trust safeguards complement rather than supersede object and field authorization. The recurring problem here is a case-summary prompt may contain personal contact information that must not be exposed beyond authorization. The correction must ensure that supplier prices are never shown outside entitled teams. The originally selected control “Audit sensitive-field access and verify prompt inputs before release; review it as part of periodic access and quality reviews” is more specific because the Trust Layer supplies security and privacy safeguards but cannot replace data permissions.
This safeguard, “Review user grants and approved model availability together; review it with audit evidence from regression testing”, reduces a different source-defined risk: An administrator restricts which users can edit templates but leaves AI model access unrestricted. The correction must ensure that plant access boundaries are not weakened by chatbot replies. That risk depends on: Template permissions and model selection restrictions govern different risks. The recurring problem here is a case-summary prompt may contain personal contact information that must not be exposed beyond authorization. The correction must ensure that supplier prices are never shown outside entitled teams. The originally selected control “Audit sensitive-field access and verify prompt inputs before release; review it as part of periodic access and quality reviews” is more specific because the Trust Layer supplies security and privacy safeguards but cannot replace data permissions.