Guardian
| where PolicyViolatedControlFeature =~ 'Prompt Injection / Jailbreaks'
| where Severity =~ 'High'
alertDetailsOverride:
alertSeverityColumnName: Severity
alertDescriptionFormat: |
This query detects Security Integrity Checks Prompt Injection Policy Violation detected from the Guardian generated at {{TimeGenerated}}.\n\nPlease check the source for more information and investigate further
alertDisplayNameFormat: Guardian- Security Integrity Checks Prompt Injection Policy Violation detection
relevantTechniques: []
name: Guardian- Security Integrity Checks Prompt Injection Policy Violation Detection
queryFrequency: 1h
version: 1.0.0
triggerThreshold: 0
severity: High
requiredDataConnectors:
- connectorId: BoschAIShield
dataTypes:
- Guardian
tactics: []
OriginalUri: https://github.com/Azure/Azure-Sentinel/blob/master/Solutions/AIShield AI Security Monitoring/Analytic Rules/SecurityIntegrityChecksPIIVulDetection.yaml
query: |
Guardian
| where PolicyViolatedControlFeature =~ 'Prompt Injection / Jailbreaks'
| where Severity =~ 'High'
kind: Scheduled
entityMappings:
- fieldMappings:
- columnName: HostName
identifier: HostName
- columnName: NTDomain
identifier: NTDomain
entityType: Host
- fieldMappings:
- columnName: SourceIP
identifier: Address
entityType: IP
queryPeriod: 1h
triggerOperator: gt
eventGroupingSettings:
aggregationKind: SingleAlert
id: d6b3372a-0fc4-40ec-9630-b96efb527fba
status: Available
description: |
'This alert creates an incident when Security Integrity Checks Prompt Injection Policy Violation detected from the Guardian.'