Add new Alerter: IDMEF with Prelude SIEM

IDMEF (RFC 4765) is intended to be a standard data format that automated
intrusion detection systems can use to report alerts about events
that they deem suspicious.

Prelude SIEM is an OpenSource SIEM: https://www.prelude-siem.org

.travis.yml

@@ -4,6 +4,8 @@ python:
 env:
 - TOXENV=docs
 - TOXENV=py36
+before_install:
+  - sudo apt-get -y install python3.6-prelude
 install:
 - pip install tox
 - >

Dockerfile-test

@@ -1,7 +1,7 @@
 FROM ubuntu:latest
 
 RUN apt-get update && apt-get upgrade -y
-RUN apt-get -y install build-essential python3.6 python3.6-dev python3-pip libssl-dev git
+RUN apt-get -y install build-essential python3.6 python3.6-dev python3-pip libssl-dev git python3.6-prelude
 
 WORKDIR /home/elastalert
 

README.md

@@ -57,6 +57,7 @@ Currently, we have built-in support for the following alert types:
 - Gitter
 - Line Notify
 - Zabbix
+- IDMEF
 
 Additional rule types and alerts can be easily imported or written.
 

docs/source/ruletypes.rst

@@ -2243,3 +2243,36 @@ Required:
 ``zbx_sender_port``: The port where zabbix server is listenning.
 ``zbx_host``: This field setup the host in zabbix that receives the value sent by Elastalert.
 ``zbx_item``: This field setup the item in the host that receives the value sent by Elastalert.
+
+
+IDMEF
+~~~~~~~~~~~
+
+IDMEF will send notification to a Prelude SIEM server (https://www.prelude-siem.org). With this alert, you will send all the notables or suspicious events to IDMEF standard format (RFC 4765: https://tools.ietf.org/html/rfc4765). Events are enriched to facilitate automation and correlation processes but also to provide as much information to the operator (contextualization alerts) to allow it to respond quickly and effectively.
+
+Required:
+
+``alert_fields``: Define how to fill an IDMEF message. This is a "key: value" list and all keys refer to an IDMEF class. Possible keys:
+         * classification: alert.classification.text,
+         * description: alert.assessment.impact.description,
+         * severity: alert.assessment.impact.severity,
+         * impact_type: alert.assessment.impact.type,
+         * target_address: alert.target.node.address.address,
+         * target_port: alert.target.service.port,
+         * target_process: alert.target.process.name,
+         * target_pid: alert.target.process.pid,
+         * src_address: alert.source.node.address.address,
+         * src_port: alert.source.service.port,
+         * user_category: alert.target(0).user.category,
+         * user_type: alert.target(0).user.user_id(0).type,
+         * user: alert.target(0).user.user_id(0).name
+
+Example usage::
+
+    alert: IDMEFAlerter
+
+    alert_fields:
+    - classification: "Abnormally high quantity of logs"
+    - description: "The host {hostname} is generating an abnormally high quantity of logs ({spike_count} while {reference_count} were generated in the last time frame)"
+    - severity: "medium"
+    - impact_type: "other"

elastalert/alerts.py

@@ -4,6 +4,7 @@
 import json
 import logging
 import os
+import pkg_resources
 import re
 import subprocess
 import sys
@@ -18,6 +19,7 @@
 from smtplib import SMTPAuthenticationError
 from smtplib import SMTPException
 from socket import error
+from prelude import ClientEasy, IDMEF
 
 import boto3
 import requests
@@ -2182,3 +2184,144 @@ def get_info(self):
             'type': 'hivealerter',
             'hive_host': self.rule.get('hive_connection', {}).get('hive_host', '')
         }
+
+
+class IDMEFAlerter(Alerter):
+    """Define the IDMEF alerter."""
+
+    REQUIRED = ["classification", "severity", "description"]
+
+    ALERT_CONFIG_OPTS = {
+        "classification": "alert.classification.text",
+        "description": "alert.assessment.impact.description",
+        "severity": "alert.assessment.impact.severity",
+        "impact_type": "alert.assessment.impact.type",
+        "target_address": "alert.target.node.address.address",
+        "target_port": "alert.target.service.port",
+        "target_process": "alert.target.process.name",
+        "target_pid": "alert.target.process.pid",
+        "src_address": "alert.source.node.address.address",
+        "src_port": "alert.source.service.port",
+        "user_category": "alert.target(0).user.category",
+        "user_type": "alert.target(0).user.user_id(0).type",
+        "user": "alert.target(0).user.user_id(0).name"
+    }
+
+    client = ClientEasy(
+        "prelude-ai",
+        ClientEasy.PERMISSION_IDMEF_WRITE,
+        "Prelude AI",
+        "Behavior Analyzer",
+        "CS GROUP",
+        pkg_resources.get_distribution('prelude-ai').version
+    )
+
+    try:
+        client.start()
+    except Exception as e:
+        logging.error("Error while trying to start Elastalert IDMEF Alerter: %s" % e)
+        sys.exit(1)
+
+    def __init__(self, rule):
+        # Check if all required options for alert creation are present
+        self.alerting = self._check_required(rule)
+        self.rule = rule
+
+    def _check_required(self, rule):
+        missing_fields = []
+        alert_fields = {}
+
+        try:
+            alert_fields = rule["alert_fields"]
+        except KeyError:
+            elastalert_logger.warning("Missing 'alert_fields' configuration for IDMEF alerter in the '%s' rule. "
+                                      "No alerts will be sent." % rule["name"])
+            return False
+
+        for field in self.REQUIRED:
+            if not alert_fields.get(field):
+                missing_fields.append(field)
+
+        if missing_fields:
+            elastalert_logger.warning("Required fields [%s] for IDMEF alerter are missing in the '%s' rule. No alerts"
+                                      "will be sent.", ', '.join(missing_fields), rule["name"])
+
+            return False
+
+        return True
+
+    def _add_additional_data(self, idmef, key, value_type, value):
+        idmef.set("alert.additional_data(>>).meaning", key)
+        idmef.set("alert.additional_data(-1).type", value_type)
+        idmef.set("alert.additional_data(-1).data", value)
+
+    def _add_idmef_path_value(self, idmef, match, opt_name, default=None):
+        if opt_name not in self.ALERT_CONFIG_OPTS:
+            return
+
+        alert_fields = self.rule["alert_fields"]
+        try:
+            m = {}
+            for k, v in match.items():
+                m[k.replace('.keyword', '')] = v
+
+            idmef.set(self.ALERT_CONFIG_OPTS[opt_name], alert_fields[opt_name].format(**m))
+        except (KeyError, RuntimeError):
+            if not default:
+                return
+
+            idmef.set(self.ALERT_CONFIG_OPTS[opt_name], default)
+
+    def _fill_additional_data(self, idmef, match):
+        if match.get("message"):
+            self._add_additional_data(idmef, "Original Log", "string", match["message"])
+
+        self._add_additional_data(idmef, "Rule ID", "string", self.rule["name"])
+
+        if self.rule.get("query_key"):
+            grouping_field = self.rule["query_key"]
+            if grouping_field in match:
+                self._add_additional_data(idmef, "Grouping key", "string", grouping_field)
+                self._add_additional_data(idmef, "Grouping value", "string", match[grouping_field])
+
+    def _fill_source(self, idmef, match):
+        self._add_idmef_path_value(idmef, match, "src_address")
+        self._add_idmef_path_value(idmef, match, "src_port")
+
+    def _fill_target(self, idmef, match):
+        for field in ["target_address", "target_process", "target_pid", "user", "user_category", "user_type"]:
+            self._add_idmef_path_value(idmef, match, field)
+
+    def _fill_impact_info(self, idmef, match):
+        self._add_idmef_path_value(idmef, match, "severity", default="low")
+        self._add_idmef_path_value(idmef, match, "impact_type")
+        self._add_idmef_path_value(idmef, match, "description", default=self.rule["alert_fields"]["description"])
+
+    def _fill_detect_time(self, idmef, match):
+        timestamp_field = self.rule["timestamp_field"]
+
+        detect_time = match[timestamp_field]
+        if detect_time:
+            idmef.set("alert.detect_time", detect_time)
+
+    def _fill_classification(self, idmef, match):
+        self._add_idmef_path_value(idmef, match, "classification", default=self.rule["alert_fields"]["classification"])
+
+    def alert(self, matches):
+        if not self.alerting:
+            return
+
+        for match in matches:
+            idmef = IDMEF()
+
+            self._fill_classification(idmef, match)
+            self._fill_detect_time(idmef, match)
+            self._fill_impact_info(idmef, match)
+            self._fill_source(idmef, match)
+            self._fill_target(idmef, match)
+            self._fill_additional_data(idmef, match)
+
+            self.client.sendIDMEF(idmef)
+
+    def get_info(self):
+        return {'type': 'IDMEF Alerter'}

example_rules/example_new_term_idmef.yaml

@@ -0,0 +1,72 @@
+# Alert when a login event is detected for user "admin" never before seen IP
+# In this example, "login" logs contain which user has logged in from what IP
+
+# (Optional)
+# Elasticsearch host
+# es_host: elasticsearch.example.com
+
+# (Optional)
+# Elasticsearch port
+# es_port: 14900
+
+# (OptionaL) Connect with SSL to Elasticsearch
+#use_ssl: True
+
+# (Optional) basic-auth username and password for Elasticsearch
+#es_username: someusername
+#es_password: somepassword
+
+# (Required)
+# Rule name, must be unique
+name: Example new term rule
+
+# (Required)
+# Type of alert.
+# the frequency rule type alerts when num_events events occur with timeframe time
+type: new_term
+
+# (Required)
+# Index to search, wildcard supported
+index: logstash-*
+
+# (Required, new_term specific)
+# Monitor the field ip_address
+fields:
+ - "ip_address"
+
+# (Optional, new_term specific)
+# This means that we will query 90 days worth of data when ElastAlert starts to find which values of ip_address already exist
+# If they existed in the last 90 days, no alerts will be triggered for them when they appear
+terms_window_size:
+  days: 90
+
+# (Required)
+# A list of Elasticsearch filters used for find events
+# These filters are joined with AND and nested in a filtered query
+# For more info: http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/query-dsl.html
+# We are filtering for only "login_event" type documents with username "admin"
+filter:
+- term:
+    _type: "login_event"
+- term:
+    username: admin
+
+# (Required)
+# The alert is use when a match is found
+alert:
+- "IDMEFAlerter"
+
+# (required, IDMEF specific)
+# a list of IDMEF paths to format the alert
+alert_fields:
+- src_address: "{client}"
+- src_port: "{port}"
+- target_address: "{remotehost}"
+- target_process: "{process}"
+- target_pid: "{pid}"
+- user: "{user}"
+- user_category: "os-device"
+- user_type: "target-user"
+- classification: "Unusual device behavior"
+- description: "Unusual behavior from {client} to {remotehost}."
+- severity: "medium"

example_rules/example_spike_idmef.yaml

@@ -0,0 +1,84 @@
+# Alert when there is a sudden spike in the volume of events
+
+# (Optional)
+# Elasticsearch host
+# es_host: elasticsearch.example.com
+
+# (Optional)
+# Elasticsearch port
+# es_port: 14900
+
+# (Optional) Connect with SSL to Elasticsearch
+#use_ssl: True
+
+# (Optional) basic-auth username and password for Elasticsearch
+#es_username: someusername
+#es_password: somepassword
+
+# (Required)
+# Rule name, must be unique
+name: Event spike
+
+# (Required)
+# Type of alert.
+# the spike rule type compares the number of events within two sliding windows to each other
+type: spike
+
+# (Required)
+# Index to search, wildcard supported
+index: logstash-*
+
+# (Required one of _cur or _ref, spike specific)
+# The minimum number of events that will trigger an alert
+# For example, if there are only 2 events between 12:00 and 2:00, and 20 between 2:00 and 4:00
+# _ref is 2 and _cur is 20, and the alert WILL fire because 20 is greater than threshold_cur and (_ref * spike_height)
+threshold_cur: 5
+#threshold_ref: 5
+
+# (Required, spike specific)
+# The size of the window used to determine average event frequency
+# We use two sliding windows each of size timeframe
+# To measure the 'reference' rate and the current rate
+timeframe:
+  hours: 2
+
+# (Required, spike specific)
+# The spike rule matches when the current window contains spike_height times more
+# events than the reference window
+spike_height: 3
+
+# (Required, spike specific)
+# The direction of the spike
+# 'up' matches only spikes, 'down' matches only troughs
+# 'both' matches both spikes and troughs
+spike_type: "up"
+
+# (Required)
+# A list of Elasticsearch filters used for find events
+# These filters are joined with AND and nested in a filtered query
+# For more info: http://www.elasticsearch.org/guide/en/elasticsearch/reference/current/query-dsl.html
+filter:
+- query:
+    query_string:
+      query: "field: value"
+- type:
+    value: "some_doc_type"
+
+# (Required)
+# The alert is use when a match is found
+alert:
+- "IDMEFAlerter"
+
+# (required, IDMEF specific)
+# a list of IDMEF paths to format the alert
+alert_fields:
+- classification: "Abnormally high quantity of logs"
+- description: "The host {hostname} is generating an abnormally high quantity of logs ({spike_count} while {reference_count} were generated in the last time frame)"
+- severity: "medium"
+- impact_type: "other"
+
+# This option only keep count in memory
+use_terms_query: true
+
+# Force doc_type needed for use_terms_query option
+doc_type: "events"

requirements.txt

@@ -21,3 +21,4 @@ requests>=2.0.0
 stomp.py>=4.1.17
 texttable>=0.8.8
 twilio==6.0.0
+prelude>=5.0

setup.py

@@ -48,6 +48,7 @@
         'texttable>=0.8.8',
         'twilio>=6.0.0,<6.1',
         'python-magic>=0.4.15',
-        'cffi>=1.11.5'
+        'cffi>=1.11.5',
+        'prelude>=5.0'
     ]
 )