Merge branch 'master' into domain_object

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/Bitcoin.py

@@ -1,142 +0,0 @@
-#!/usr/bin/env python3
-# -*-coding:UTF-8 -*
-"""
-The Bitcoin Module
-============================
-
-It trying to extract Bitcoin address and secret key from paste
-
-    ..seealso:: Paste method (get_regex)
-
-Requirements
-------------
-
-*Need running Redis instances. (Redis).
-
-"""
-
-from packages import Paste
-from Helper import Process
-from pubsublogger import publisher
-
-import re
-import time
-import redis
-
-from hashlib import sha256
-
-
-#### thank http://rosettacode.org/wiki/Bitcoin/address_validation#Python for this 2 functions
-
-def decode_base58(bc, length):
-    n = 0
-    for char in bc:
-        n = n * 58 + digits58.index(char)
-    return n.to_bytes(length, 'big')
-
-def check_bc(bc):
-    try:
-        bcbytes = decode_base58(bc, 25)
-        return bcbytes[-4:] == sha256(sha256(bcbytes[:-4]).digest()).digest()[:4]
-    except Exception:
-        return False
-########################################################
-
-def search_key(content, message, paste):
-    bitcoin_address = re.findall(regex_bitcoin_public_address, content)
-    bitcoin_private_key = re.findall(regex_bitcoin_private_key, content)
-    date = str(paste._get_p_date())
-    validate_address = False
-    key = False
-    if(len(bitcoin_address) >0):
-        #print(message)
-        for address in bitcoin_address:
-            if(check_bc(address)):
-                validate_address = True
-                print('Bitcoin address found : {}'.format(address))
-                if(len(bitcoin_private_key) > 0):
-                    for private_key in bitcoin_private_key:
-                        print('Bitcoin private key found : {}'.format(private_key))
-                        key = True
-                # build bitcoin correlation
-                save_cryptocurrency_data('bitcoin', date, message, address)
-
-        if(validate_address):
-            p.populate_set_out(message, 'Duplicate')
-            to_print = 'Bitcoin found: {} address and {} private Keys'.format(len(bitcoin_address), len(bitcoin_private_key))
-            print(to_print)
-            publisher.warning(to_print)
-
-            msg = 'infoleak:automatic-detection="bitcoin-address";{}'.format(message)
-            p.populate_set_out(msg, 'Tags')
-
-            if(key):
-                msg = 'infoleak:automatic-detection="bitcoin-private-key";{}'.format(message)
-                p.populate_set_out(msg, 'Tags')
-
-                to_print = 'Bitcoin;{};{};{};'.format(paste.p_source, paste.p_date,
-                                                    paste.p_name)
-                publisher.warning('{}Detected {} Bitcoin private key;{}'.format(
-                    to_print, len(bitcoin_private_key),paste.p_rel_path))
-
-def save_cryptocurrency_data(cryptocurrency_name, date, item_path, cryptocurrency_address):
-    # create basic medata
-    if not serv_metadata.exists('cryptocurrency_metadata_{}:{}'.format(cryptocurrency_name, cryptocurrency_address)):
-        serv_metadata.hset('cryptocurrency_metadata_{}:{}'.format(cryptocurrency_name, cryptocurrency_address), 'first_seen', date)
-        serv_metadata.hset('cryptocurrency_metadata_{}:{}'.format(cryptocurrency_name, cryptocurrency_address), 'last_seen', date)
-    else:
-        last_seen = serv_metadata.hget('cryptocurrency_metadata_{}:{}'.format(cryptocurrency_name, cryptocurrency_address), 'last_seen')
-        if not last_seen:
-            serv_metadata.hset('cryptocurrency_metadata_{}:{}'.format(cryptocurrency_name, cryptocurrency_address), 'last_seen', date)
-        else:
-            if int(last_seen) < int(date):
-                serv_metadata.hset('cryptocurrency_metadata_{}:{}'.format(cryptocurrency_name, cryptocurrency_address), 'last_seen', date)
-
-    # global set
-    serv_metadata.sadd('set_cryptocurrency_{}:{}'.format(cryptocurrency_name, cryptocurrency_address), item_path)
-
-    # daily
-    serv_metadata.hincrby('cryptocurrency:{}:{}'.format(cryptocurrency_name, date), cryptocurrency_address, 1)
-
-    # all type
-    serv_metadata.zincrby('cryptocurrency_all:{}'.format(cryptocurrency_name), cryptocurrency_address, 1)
-
-    # item_metadata
-    serv_metadata.sadd('item_cryptocurrency_{}:{}'.format(cryptocurrency_name, item_path), cryptocurrency_address)
-
-if __name__ == "__main__":
-    publisher.port = 6380
-    publisher.channel = "Script"
-
-    config_section = 'Bitcoin'
-
-    # Setup the I/O queues
-    p = Process(config_section)
-
-    serv_metadata = redis.StrictRedis(
-        host=p.config.get("ARDB_Metadata", "host"),
-        port=p.config.getint("ARDB_Metadata", "port"),
-        db=p.config.getint("ARDB_Metadata", "db"),
-        decode_responses=True)
-
-    # Sent to the logging a description of the module
-    publisher.info("Run Keys module ")
-
-    digits58 = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
-
-    regex_bitcoin_public_address = re.compile(r'(?<![a-km-zA-HJ-NP-Z0-9])[13][a-km-zA-HJ-NP-Z0-9]{26,33}(?![a-km-zA-HJ-NP-Z0-9])')
-    regex_bitcoin_private_key = re.compile(r'[5KL][1-9A-HJ-NP-Za-km-z]{50,51}')
-
-    # 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
-        paste = Paste.Paste(message)
-        content = paste.get_p_content()
-        search_key(content, message, paste)

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/Keys.py

@@ -121,6 +121,13 @@ def search_key(paste):
         p.populate_set_out(msg, 'Tags')
         find = True
 
+    if '-----BEGIN PUBLIC KEY-----' in content:
+        publisher.warning('{} has a public key message'.format(paste.p_name))
+
+        msg = 'infoleak:automatic-detection="public-key";{}'.format(message)
+        p.populate_set_out(msg, 'Tags')
+        find = True
+
     # pgp content
     if get_pgp_content:
         p.populate_set_out(message, 'PgpDump')

bin/LAUNCH.sh

@@ -186,7 +186,9 @@ function launching_scripts {
     sleep 0.1
     screen -S "Script_AIL" -X screen -t "Decoder" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./Decoder.py; read x"
     sleep 0.1
-    screen -S "Script_AIL" -X screen -t "Bitcoin" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./Bitcoin.py; read x"
+    screen -S "Script_AIL" -X screen -t "Cryptocurrency" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./Cryptocurrencies.py; read x"
+    sleep 0.1
+    screen -S "Script_AIL" -X screen -t "Tools" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./Tools.py; read x"
     sleep 0.1
     screen -S "Script_AIL" -X screen -t "Phone" bash -c "cd ${AIL_BIN}; ${ENV_PY} ./Phone.py; read x"
     sleep 0.1
@@ -213,6 +215,8 @@ 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/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

configs/core.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 =

requirements.txt

@@ -50,6 +50,7 @@ flask-login
 bcrypt
 
 #DomainClassifier
+git+https://github.com/D4-project/BGP-Ranking.git/#egg=pybgpranking&subdirectory=client
 DomainClassifier
 #Indexer requirements
 whoosh