---
schema_version: "1"
id: 8568ab301cecf7de79ae5f6269137d2129b296077a43f19b07124e796aec615c
title: Turn On Prompt Injection Detection for Prompts (Beta)
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/ai/264-0-0/generative_ai_trust_configure_prompt_injection_detection.md
canonical_url: https://help.salesforce.com/s/articleView?id=ai.generative_ai_trust_configure_prompt_injection_detection.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: a9a8b0749e1639d3c319563bef0aaa2cd8019731cecd46eb669ff9011c0796d2
description: Turn on prompt injection detection in Einstein Trust Layer Setup to monitor content that attempts to make the large language model do something that it isn’t designed to do. These settings are applied at the Salesforce org level.
products:
  - Agentforce
  - Cross Cloud
release: "264"
---
# Turn On Prompt Injection Detection for Prompts (Beta)

Turn on prompt injection detection in Einstein Trust Layer Setup to monitor content that attempts to make the large language model do something that it isn’t designed to do. These settings are applied at the Salesforce org level.

### Required Editions

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small edition"><colgroup><col></colgroup><tbody><tr class=""><td class="slds-cell-wrap" style="vertical-align:top;">Available in: <strong>Enterprise</strong>, <strong>Performance</strong>, and <strong>Unlimited</strong> Editions with an Einstein for Sales, Einstein for Platform, Einstein for Service, Einstein 1 Service, or Einstein GPT Service add-on. To purchase add-ons, contact your Salesforce account executive.</td></tr></tbody></table>

<table class="slds-table slds-table_bordered slds-max-medium-table_stacked slds-m-bottom_small permission">
        <colgroup>
          <col style="width:50%">
          <col style="width:50%">
        </colgroup>
        <thead class="slds-text-title_caps ">
          <tr class="">
            <th scope="colgroup" class="slds-cell-wrap" colspan="2" style="text-align:center;vertical-align:top;" id="d68161e64">User Permissions
              Needed</th>
          </tr>
        </thead>
        <tbody>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d68161e64 ">To turn on prompt injection detection:</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d68161e64 ">View Setup </td>

          </tr>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d68161e64 ">&nbsp;</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d68161e64 ">AND</td>

          </tr>
          <tr class="">
            <td data-label="User Permissions Needed" class="slds-cell-wrap" style="vertical-align:top;" headers="d68161e64 ">&nbsp;</td>

            <td class="slds-cell-wrap" style="vertical-align:top;" headers="d68161e64 ">Customize Application</td>

          </tr>
        </tbody>
      </table>

Einstein Generative AI must be enabled.

![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_note.png)

Note Prompt Injection Detection is a beta feature.

1. From Setup, in the Quick Find field, enter Einstein, and then select **Einstein Trust Layer**.
    
    ![Note](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/images/icon_note.png)
    
    Note If you can’t find **Einstein Generative AI Setup**, make sure that your org meets the prerequisites for any generative AI features you plan to use. For more support, contact your Salesforce account executive (AE).
2. Click **Safety & Security**.
3. Review the beta service terms. Turn on prompt injection detection.
4. Use the [reports and dashboards in Data 360](https://help.salesforce.com/s/articleView?id=ai.generative_ai_feedback_analytics.htm&release=264.0.0&type=5 "Share insights from your org’s Einstein generative AI audit and feedback data with your team. Use pre-built dashboards and reports, running queries, and building Data 360 reports.") to see if prompt injections have been detected.
    
    ![A toggle switch to enable quick detection of prompt injection, which is currently disabled.](https://sf-zdocs-cdn-prod.zoominsoftware.com/tdta-ai-generative_ai-264-0-0-production-enus/f8ef6498-d7b2-44e3-9b34-ffd5a850aae9/generative_ai/images/trust_layer_prompt_injection_detection_setup.png)

#### See Also

- [Prompt Injection Detection (Beta)](https://help.salesforce.com/s/articleView?id=ai.generative_ai_trust_prompt_injection_detection.htm&release=264.0.0&type=5 "Prompt Injection, sometimes referred to as “jailbreak,” is a large language model (LLM) vulnerability. Prompt injections are attempts to make the LLM do something that it isn’t designed to do. Hackers can create prompts that attempt to override the system policies or manipulate the LLM into doing something unintended.")