o365beat.yml

################### O365beat Configuration Example #########################

############################# O365beat ######################################

o365beat:
  ## period defines how often API is polled for new content blobs
  ## 5 min default, as new content (probably) isn't published too often
  # period: 5m

  # period Defines how often API is polled for new content blobs
  # 5 min default, as new content (probably) isn't published too often
  # period: 5m

  # api_timeout Defines how long the beat will wait for responses from the API
  # 30 second default; extend this for busy tenants
  # api_timeout: 30s

  # content_max_age Defines the oldest content the beat will request
  # 7 day default, which is the max retained according to Microsoft
  # reduce this for busy tenants to minimize risk of timeouts
  # content_max_age: 168h

  ## pull secrets from environment (e.g, > set -a; . ./ENV_FILE; set +a;)
  ## or a key store (https://www.elastic.co/guide/en/beats/filebeat/current/keystore.html)
  ## or hard-code here:
  tenant_domain: ${O365BEAT_TENANT_DOMAIN:}
  client_secret: ${O365BEAT_CLIENT_SECRET:}
  client_id:     ${O365BEAT_CLIENT_ID:}     # aka application id (GUID)
  directory_id:  ${O365BEAT_DIRECTORY_ID:}  # aka tenant id (GUID)
  registry_file_path: ${O365BEAT_REGISTRY_PATH:./o365beat.state}
  certificate_path:   ${O365BEAT_CERTIFICATE_PATH:} #path to your .pfx file
  certificate_pwd:    ${O365BEAT_CERTIFICATE_PWD:} #password of your .pfx file

  ## the following content types will be pulled from the API
  ## for available types, see https://docs.microsoft.com/en-us/office/office-365-management-api/office-365-management-activity-api-reference#working-with-the-office-365-management-activity-api
  content_types:
    - Audit.AzureActiveDirectory
    - Audit.Exchange
    - Audit.SharePoint
    - Audit.General
    # - DLP.All # TODO: figure out what to do with this, it's not like the rest

## By default, map Office 365 Activities API event fields to ECS fields
## API "Common" fields: Id, RecordType, CreationTime, Operation, OrganizationId,
##                      UserType, UserKey, Workload, ResultStatus, ObjectId,
##                      UserId, ClientIP, Scope
processors:
  - dissect:
      field: UserId
      tokenizer: '%{user.name}@%{user.domain}'
      when:
        contains:
          UserId: '@'
  - dissect:
      field: ClientIP
      tokenizer: '[%{clientip}]:%{clientport}'
      when:
        contains:
          ClientIP: '['
  - dissect:
      field: ClientIP
      tokenizer: '%{clientip}:%{clientport}'
      when:
        contains:
          ClientIP: ':'
        not:
          contains:
            ClientIP: '['
  - convert:
      fields:
        - {from: Id, to: 'event.id', type: string}                # ecs core
        - {from: RecordType, to: 'event.code', type: string}      # ecs extended
        - {from: Operation, to: 'event.action', type: string}     # ecs core
        - {from: OrganizationId, to: 'cloud.account.id', type: string} # ecs extended
        # - {from: UserType, to: '', type: ''}                    # no ecs mapping
        # - {from: UserKey, to: '', type: ''}                     # no ecs mapping
        - {from: Workload, to: 'event.category', type: string}    # ecs core
        - {from: ResultStatus, to: 'event.outcome', type: string} # ecs extended
        # - {from: ObjectId, to: '', type: ''}                    # no ecs mapping
        - {from: UserId, to: 'user.id', type: string}             # ecs core
        - {from: ClientIP, to: 'client.ip', type: ip}             # ecs core
        - {from: 'dissect.clientip', to: 'client.ip', type: ip}   # ecs core
        # - {from: "Scope", to: "", type: ""}                     # no ecs mapping
        # the following fields use the challenging array-of-name-value-pairs format
        # converting them to strings fixes issues in elastic, eases non-script parsing
        # easier to rehydrate into arrays from strings than vice versa:
        - {from: Parameters, type: string}                        # no ecs mapping
        - {from: ExtendedProperties, type: string}                # no ecs mapping
        - {from: ModifiedProperties, type: string}                # no ecs mapping
      ignore_missing: true
      fail_on_error: false
      mode: copy # default

#================================ General =====================================

# The name of the shipper that publishes the network data. It can be used to group
# all the transactions sent by a single shipper in the web interface.
#name:

# The tags of the shipper are included in their own field with each
# transaction published.
#tags: ["service-X", "web-tier"]

# Optional fields that you can specify to add additional information to the
# output.
#fields:
#  env: staging


#============================== Dashboards =====================================
# These settings control loading the sample dashboards to the Kibana index. Loading
# the dashboards is disabled by default and can be enabled either by setting the
# options here or by using the `setup` command.
#setup.dashboards.enabled: false

# The URL from where to download the dashboards archive. By default this URL
# has a value which is computed based on the Beat name and version. For released
# versions, this URL points to the dashboard archive on the artifacts.elastic.co
# website.
#setup.dashboards.url:

#============================== Kibana =====================================

# Starting with Beats version 6.0.0, the dashboards are loaded via the Kibana API.
# This requires a Kibana endpoint configuration.
setup.kibana:

  # Kibana Host
  # Scheme and port can be left out and will be set to the default (http and 5601)
  # In case you specify and additional path, the scheme is required: http://localhost:5601/path
  # IPv6 addresses should always be defined as: https://[2001:db8::1]:5601
  #host: "localhost:5601"

  # Kibana Space ID
  # ID of the Kibana Space into which the dashboards should be loaded. By default,
  # the Default Space will be used.
  #space.id:

#============================= Elastic Cloud ==================================

# These settings simplify using O365beat with the Elastic Cloud (https://cloud.elastic.co/).

# The cloud.id setting overwrites the `output.elasticsearch.hosts` and
# `setup.kibana.host` options.
# You can find the `cloud.id` in the Elastic Cloud web UI.
#cloud.id:

# The cloud.auth setting overwrites the `output.elasticsearch.username` and
# `output.elasticsearch.password` settings. The format is `<user>:<pass>`.
#cloud.auth:

#================================ Outputs =====================================

# Configure what output to use when sending the data collected by the beat.

#-------------------------- Elasticsearch output ------------------------------
output.elasticsearch:
  # Array of hosts to connect to.
  hosts: ["localhost:9200"]

  # Optional protocol and basic auth credentials.
  #protocol: "https"
  #username: "elastic"
  #password: "changeme"

#----------------------------- Logstash output --------------------------------
#output.logstash:
  # The Logstash hosts
  #hosts: ["localhost:5044"]

  # Optional SSL. By default is off.
  # List of root certificates for HTTPS server verifications
  #ssl.certificate_authorities: ["/etc/pki/root/ca.pem"]

  # Certificate for SSL client authentication
  #ssl.certificate: "/etc/pki/client/cert.pem"

  # Client Certificate Key
  #ssl.key: "/etc/pki/client/cert.key"

#================================ Processors =====================================

# Configure processors to enhance or manipulate events generated by the beat.

# processors:
#   - add_host_metadata: ~
#   - add_cloud_metadata: ~
#   - add_docker_metadata: ~

#================================ Logging =====================================

# Sets log level. The default log level is info.
# Available log levels are: error, warning, info, debug
#logging.level: debug

# At debug level, you can selectively enable logging only for some components.
# To enable all selectors use ["*"]. Examples of other selectors are "beat",
# "publish", "service".
#logging.selectors: ["*"]

#============================== X-Pack Monitoring ===============================
# o365beat can export internal metrics to a central Elasticsearch monitoring
# cluster.  This requires xpack monitoring to be enabled in Elasticsearch.  The
# reporting is disabled by default.

# Set to true to enable the monitoring reporter.
#monitoring.enabled: false

# Sets the UUID of the Elasticsearch cluster under which monitoring data for this
# O365beat instance will appear in the Stack Monitoring UI. If output.elasticsearch
# is enabled, the UUID is derived from the Elasticsearch cluster referenced by output.elasticsearch.
#monitoring.cluster_uuid:

# Uncomment to send the metrics to Elasticsearch. Most settings from the
# Elasticsearch output are accepted here as well.
# Note that the settings should point to your Elasticsearch *monitoring* cluster.
# Any setting that is not set is automatically inherited from the Elasticsearch
# output configuration, so if you have the Elasticsearch output configured such
# that it is pointing to your Elasticsearch monitoring cluster, you can simply
# uncomment the following line.
#monitoring.elasticsearch:

#================================= Migration ==================================

# This allows to enable 6.7 migration aliases
#migration.6_to_7.enabled: true