---
schema_version: "1"
id: 56e17a97ecb62b050ea376c06e2b46ec478d568bec17d06f8044eb2a75d99525
title: Prompt Injection Detection (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_prompt_injection_detection.md
canonical_url: https://help.salesforce.com/s/articleView?id=ai.generative_ai_trust_prompt_injection_detection.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: aa0a922949859780953fc17fa3b7c9d3198404598f88b4d387f559305aa4168d
description: 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.
products:
  - Agentforce
  - Cross Cloud
release: "264"
---
# Prompt Injection Detection (Beta)

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.

### 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>

Prompt injections can be introduced directly in the prompt text or indirectly through data sources included in the prompt.

Salesforce Prompt Injection Detection models recognize these types of prompt injection attacks:

 
| Type | Description |
| --- | --- |
| Pretending (role-play) | Prompts that instruct the AI to adopt a different system persona with malicious intent, and use deceptive or misleading language to manipulate it in social engineering attacks |
| Privilege escalation or attempts to change system rules | Prompts that have harmful commands to get around or change system rules and bypass safety training for language models, including attacks that break security restrictions such as Do Anything Now (DAN) jailbreak attacks |
| Prompt leakage intent | Prompts designed to gather sensitive information from the language model, such as the system policies and knowledge documents, to gain unauthorized information |
| Encoding attacks | Using obfuscated or hidden messages in prompts to make a language model produce malicious, unaligned, or toxic content |
| Privacy attacks | Prompts that try to get personal or confidential information to gain unauthorized access to data or misuse the information |
| Malicious code generation | Prompts that attempt to produce harmful computer code, such as malware, viruses, or tools or software designed to commit fraud and other malicious intent. |

If prompt injection is detected, the content is rated and the score is logged in the audit trail and stored in Data 360. You can view prompt injection scores in Data 360 DMOs.

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

Important Although our prompt injection detection models have shown to be effective during internal testing, it's important to note that no model can guarantee 100% accuracy. With trust as our priority, we're dedicated to the ongoing evaluation and refinement of our models.

#### See Also

- [Turn On Prompt Injection Detection for Prompts (Beta)](https://help.salesforce.com/s/articleView?id=ai.generative_ai_trust_configure_prompt_injection_detection.htm&release=264.0.0&type=5 "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.")