Merge branch 'master' of https://github.com/CIRCL/AIL-framework

README.md

@@ -42,8 +42,8 @@ Features
 * Multiple feed support
 * Each module can process and reprocess the information already processed by AIL
 * Detecting and extracting URLs including their geographical location (e.g. IP address location)
-* Extracting and validating potential leak of credit cards numbers, credentials, ...
+* Extracting and validating potential leaks of credit card numbers, credentials, ...
-* Extracting and validating email addresses leaked including DNS MX validation
+* Extracting and validating leaked email addresses, including DNS MX validation
 * Module for extracting Tor .onion addresses (to be further processed for analysis)
 * Keep tracks of duplicates (and diffing between each duplicate found)
 * Extracting and validating potential hostnames (e.g. to feed Passive DNS systems)

bin/IPAddress.py

@@ -0,0 +1,81 @@
+#!/usr/bin/env python3
+# -*-coding:UTF-8 -*
+"""
+The IP Module
+======================
+
+This module is consuming the global channel.
+
+It first performs a regex to find IP addresses and then matches those IPs to 
+some configured ip ranges.
+
+The list of IP ranges are expected to be in CIDR format (e.g. 192.168.0.0/16)
+and should be defined in the config.cfg file, under the [IP] section
+
+"""
+
+import time
+import re
+from pubsublogger import publisher
+from packages import Paste
+from Helper import Process
+from ipaddress import IPv4Network, IPv4Address
+
+
+def search_ip(message):
+    paste = Paste.Paste(message)
+    content = paste.get_p_content()
+    # regex to find IPs
+    reg_ip = re.compile(r'^(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)', flags=re.MULTILINE)
+    # list of the regex results in the Paste, may be null
+    results = reg_ip.findall(content)
+    matching_ips = []
+
+    for res in results:
+        address = IPv4Address(res)
+        for network in ip_networks:
+            if address in network:
+                matching_ips.append(address)
+
+    if len(matching_ips) > 0:
+        print('{} contains {} IPs'.format(paste.p_name, len(matching_ips)))
+        publisher.warning('{} contains {} IPs'.format(paste.p_name, len(matching_ips)))
+
+        #Tag message with IP
+        msg = 'infoleak:automatic-detection="ip";{}'.format(message)
+        p.populate_set_out(msg, 'Tags')
+        #Send to duplicate
+        p.populate_set_out(message, 'Duplicate')
+
+if __name__ == '__main__':
+    # If you wish to use an other port of channel, do not forget to run a subscriber accordingly (see launch_logs.sh)
+    # Port of the redis instance used by pubsublogger
+    publisher.port = 6380
+    # Script is the default channel used for the modules.
+    publisher.channel = 'Script'
+
+    # Section name in bin/packages/modules.cfg
+    config_section = 'IP'
+    # Setup the I/O queues
+    p = Process(config_section)
+
+    ip_networks = []
+    for network in p.config.get("IP", "networks").split(","):
+        ip_networks.append(IPv4Network(network))
+
+
+    # Sent to the logging a description of the module
+    publisher.info("Run IP module")
+
+    # Endless loop getting messages from the input queue
+    while True:
+        # Get one message from the input queue
+        message = p.get_from_set()
+        if message is None:
+            publisher.debug("{} queue is empty, waiting".format(config_section))
+            time.sleep(1)
+            continue
+
+        # Do something with the message from the queue
+        search_ip(message)
+

bin/LAUNCH.sh

@@ -213,6 +213,8 @@ function launching_scripts {
     screen -S "Script_AIL" -X screen -t "UpdateBackground" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./update-background.py; read x"
     sleep 0.1
     screen -S "Script_AIL" -X screen -t "SubmitPaste" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./submit_paste.py; read x"
+    sleep 0.1
+    screen -S "Script_AIL" -X screen -t "IPAddress" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./IPAddress.py; read x"
 
 }
 

bin/packages/config.cfg.sample

@@ -266,3 +266,8 @@ default_crawler_closespider_pagecount = 50
 default_crawler_user_agent = Mozilla/5.0 (Windows NT 6.1; rv:60.0) Gecko/20100101 Firefox/60.0
 splash_url = http://127.0.0.1
 splash_port = 8050-8052
+
+[IP]
+# list of comma-separated CIDR that you wish to be alerted for. e.g:
+#networks = 192.168.34.0/24,10.0.0.0/8,192.168.33.0/24
+networks =

bin/packages/modules.cfg

@@ -132,3 +132,7 @@ publish = Redis_Mixer
 [Crawler]
 subscribe = Redis_Crawler
 publish = Redis_Mixer,Redis_Tags
+
+[IP]
+subscribe = Redis_Global
+publish = Redis_Duplicate,Redis_Tags