LoFP LoFP / approved prompt-security tests that send known jailbreak strings, such as dan or \"ignore previous instructions\". exclude that source ip or api management subscription.

Techniques

Sample rules

Microsoft Foundry Jailbreak Detected

Description

Detects a Microsoft Foundry chat, sent through API Management, where Azure sets jailbreak.detected on the prompt. The flag is on the prompt filter when the call is allowed through, and on the error body when the filter blocks the call.

Detection logic

from logs-azure_ai_foundry.logs-* metadata _id, _version, _index
| where
    data_stream.dataset == "azure_ai_foundry.logs" and
    azure.ai_foundry.category == "GatewayLogs" and
    (
        azure.ai_foundry.properties.backend_response_body.prompt_filter_results.content_filter_results.jailbreak.detected == true or
        azure.ai_foundry.properties.backend_response_body.error.innererror.content_filter_result.jailbreak.detected == true or
        azure.ai_foundry.properties.backend_response_body.choices.content_filter_results.jailbreak.detected == true
    )
| keep
    _id,
    _version,
    _index,
    @timestamp,
    source.ip,
    azure.ai_foundry.properties.user_agent,
    azure.ai_foundry.properties.apim_subscription_id,
    azure.ai_foundry.properties.api_id,
    azure.ai_foundry.properties.operation_id,
    azure.ai_foundry.properties.backend_response_body.model,
    azure.ai_foundry.properties.backend_response_code,
    azure.ai_foundry.service_name,
    azure.resource.group,
    url.domain,
    url.path,
    source.geo.country_iso_code,
    source.geo.city_name,
    source.as.organization.name,
    azure.ai_foundry.properties.backend_request_body.messages.content,
    azure.ai_foundry.properties.backend_response_body.choices.message.content,
    azure.ai_foundry.properties.backend_response_body.prompt_filter_results.content_filter_results.jailbreak.detected,
    azure.ai_foundry.properties.backend_response_body.error.innererror.content_filter_result.jailbreak.detected,
    azure.ai_foundry.properties.backend_response_body.choices.content_filter_results.jailbreak.detected