Name:Cisco AI Defense Allowed Sensitive Prompt id:75f06fd6-2b31-4ca4-9aaf-56448c342e44 version:1 date:None author:Nasreddine Bencherchali, Splunk status:production type:TTP Description:Detects Cisco AI Defense prompt events that were allowed and matched a privacy guardrail for personally identifiable information or payment card data.
These events may indicate that sensitive information was submitted to an AI application and should be reviewed against the organization's data handling policy. Data_source:
application_name=if(isnotnull('genai_application.application_name') AND len(trim('genai_application.application_name'))>0, 'genai_application.application_name', "unknown"),
connection_name=if(isnotnull('connection.connection_name') AND len(trim('connection.connection_name'))>0, 'connection.connection_name', "unknown"),
application_key=if(isnotnull(application_id) AND len(trim(application_id))>0, application_id, application_name),
connection_key=if(isnotnull(connection_id) AND len(trim(connection_id))>0, connection_id, connection_name),
policy_name='policy.policy_name',
event_time=_time
| where mvfind('event_policy_guardrail_assocs{}.policy_guardrail_assoc.guardrail_avail_ruleset.guardrail_ruleset_type', "(?i)\\bPII\\b|personally identifiable information|\\bPCI\\b|payment card industry")>=0
| bin _time span=10m
| stats count as event_count dc(event_id) as distinct_event_count min(event_time) as firstTime max(event_time) as lastTime values(event_id) as event_ids values(guardrail_ruleset_type) as guardrail_ruleset_types values(guardrail_entity_name) as guardrail_entity_names values(policy_name) as policy_names values(application_name) as application_names values(connection_name) as connection_names by _time application_key connection_key
how_to_implement:Install and configure the Cisco Security Cloud app to ingest Cisco AI Defense alerts into Splunk with the cisco:ai:defense sourcetype.
Confirm that extraction is enabled for the required fields as shown in the detection search.
Configure the "cisco_ai_defense" macro to match the index, source, and sourcetype used in your environment.
The search groups matching prompt events by application and connection in ten-minute windows to reduce duplicate findings. known_false_positives:Authorized testing, demonstrations, synthetic data, or approved workflows may submit content that matches PII or PCI guardrails.
Review the application, connection, policy, guardrail entity, and data handling requirements before treating an event as a policy violation. References: drilldown_searches: name:'View the detection results for - "$application_names$"' search:'%original_detection_search% | search application_names="$application_names$"' earliest_offset:'$info_min_time$' latest_offset:'$info_max_time$' analytic_story:['Abuse of GenAI Systems and Applications', 'Data Protection', 'Critical Alerts']
