def process(file, dst, type):
hashes = set()
with open(file, 'r') as f_in:
for obj in csv.DictReader(f_in):
pem = obj['PEM Info'].strip("'").replace('\r',
'').replace('\n\n', '\n')
try:
obj['Certificate Name']
except:
obj['Common Name or Certificate Name']
cert = load_certificate(FILETYPE_PEM, pem)
hashes.add(gethash(cert, 'md5'))
hashes.add(gethash(cert, 'sha1'))
hashes.add(obj['SHA-256 Fingerprint'].lower())
warninglist = {
'name':
'Fingerprint of {type}'.format(type=type),
'version':
get_version(),
'description':
"Fingerprint of {type} taken from Mozilla's lists at https://wiki.mozilla.org/CA"
.format(type=type),
'list':
hashes,
'type':
'string',
'matching_attributes': [
"md5", "sha1", "sha256", "filename|md5", "filename|sha1",
"filename|sha256", "x509-fingerprint-md5", "x509-fingerprint-sha1",
"x509-fingerprint-sha256"
]
}
write_to_file(warninglist, dst)
def process(url, warninglist, dst):
whitelist = download(url).text
whitelist = list(set(whitelist.split()))
warninglist['type'] = 'hostname'
warninglist['matching_attributes'] = ['domain', 'hostname', 'url']
warninglist['version'] = get_version()
warninglist['list'] = whitelist
write_to_file(warninglist, dst)
def process(url, dst):
warninglist = {
'name': 'Specialized list of {} addresses belonging to common VPN providers and datacenters'.format(dst.split('-')[1].replace('ip', 'IP')),
'version': get_version(),
'description': 'Specialized list of {} addresses belonging to common VPN providers and datacenters'.format(dst.split('-')[1].replace('ip', 'IP')),
'list': process_stream(url),
'type': 'cidr',
'matching_attributes': ["ip-src", "ip-dst", "domain|ip"]
}
write_to_file(warninglist, dst)
def generate(sites, warninglist, dst):
warninglist['version'] = get_version()
warninglist['type'] = 'string'
warninglist['matching_attributes'] = [
'hostname', 'domain', 'url', 'domain|ip']
warninglist['list'] = []
for site in sites:
v = site.decode('UTF-8').split(',')[1]
warninglist['list'].append(v.strip().replace('\\r\\n', ''))
write_to_file(warninglist, dst)
def process(warninglist_name):
description = {
'description':
'Numbers that cannot be attributed because they reserved for different purposes.',
'name': 'Unattributed phone number.',
'matching_attributes': ['phone-number', 'whois-registrant-phone'],
'type': 'regex',
'version': get_version()
}
warninglist = generate_french_warninglist()
# The list can be extended by adding other entries: `warninglist.extend(generate_some_warninglist())`
description['list'] = warninglist
write_to_file(description, warninglist_name)
def process(url, dst):
warninglist = {
'name': 'TLDs as known by IANA',
'version': get_version(),
'description': 'Event contains one or more TLDs as attribute with an IDS flag set',
'list': [],
'matching_attributes': ["hostname", "domain", "domain|ip"],
'type': 'string'
}
r = download(url)
for tld in r.text.splitlines():
if tld.startswith('#'):
continue
warninglist['list'].append(tld)
write_to_file(warninglist, dst)
def process(file, dst):
warninglist = {
'name': 'List of known Microsoft Azure Datacenter IP Ranges',
'version': get_version(),
'description': 'Microsoft Azure Datacenter IP Ranges',
'list': [],
'matching_attributes': ["ip-src", "ip-dst", "domain|ip"],
'type': 'cidr'
}
with open(file, 'r') as json_file:
ms_azure_ip_list = json.load(json_file)
for value in ms_azure_ip_list['values']:
warninglist['list'] += value['properties']['addressPrefixes']
write_to_file(warninglist, dst)
def process(files, dst):
warninglist = {
'name': "List of known Cloudflare IP ranges",
'version': get_version(),
'description':
"List of known Cloudflare IP ranges (https://www.cloudflare.com/ips/)",
'type': "cidr",
'list': [],
'matching_attributes': ["ip-dst", "ip-src", "domain|ip"]
}
for file in files:
with open(file, 'r') as f:
ips = f.readlines()
for ip in ips:
warninglist['list'].append(ip.strip())
write_to_file(warninglist, dst)
def process(files, dst):
warninglist = {
'type': "string",
'matching_attributes': ["hostname", "domain", "ip-dst", "ip-src", "url", "domain|ip"],
'name': "CRL Warninglist",
'version': get_version(),
'description': "CRL Warninglist from threatstop (https://github.com/threatstop/crl-ocsp-whitelist/)",
'list': []
}
for file in files:
with open(get_abspath_source_file(file), 'r') as f:
ips = f.readlines()
for ip in ips:
warninglist['list'].append(ip.strip())
write_to_file(warninglist, dst)
def process(files, dst):
warninglist = {
'description': "Event contains one or more entries from the top 500 of the most used domains (Mozilla).",
'version': get_version(),
'name': "Top 500 domains and pages from https://moz.com/top500",
'type': 'string',
'list': [],
'matching_attributes': ['hostname', 'domain', 'uri', 'url']
}
for file in files:
with open(get_abspath_source_file(file)) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
for row in csv_reader:
v = row[1]
warninglist['list'].append(v.rstrip().rstrip('/'))
write_to_file(warninglist, dst)
def process(file, dst):
with open(get_abspath_source_file(file), newline='\n', encoding='utf-8', errors='replace') as csv_file:
sites = csv_file.readlines()[:10000]
warninglist = {
'name': 'Top 10K websites from Majestic Million',
'version': get_version(),
'description': 'Event contains one or more entries from the top 10K of the most used websites (Majestic Million).',
'matching_attributes': ['hostname', 'domain'],
'type': 'hostname',
'list': []
}
for site in sites:
v = site.split(',')[2]
warninglist['list'].append(v.rstrip())
write_to_file(warninglist, dst)
def process(file, dst, name: str, description: str):
warninglist = {
'name': name,
'version': get_version(),
'description': description,
'matching_attributes': ["ip-src", "ip-dst", "domain|ip"],
'type': 'cidr'
}
with open(get_abspath_source_file(file), 'r') as json_file:
ms_azure_ip_list = json.load(json_file)
values = []
for value in ms_azure_ip_list['values']:
values += value['properties']['addressPrefixes']
warninglist['list'] = consolidate_networks(values)
write_to_file(warninglist, dst)
def process(url, dst):
university_list = download(url).json()
warninglist = {
'type': "string",
'name': "University domains",
'matching_attributes': ['hostname', 'domain', 'url', 'domain|ip'],
'version': get_version(),
'description':
"List of University domains from https://raw.githubusercontent.com/Hipo/university-domains-list/master/world_universities_and_domains.json",
'list': []
}
for university in university_list:
for domain in university.get('domains'):
if domain not in warninglist['list']:
warninglist['list'].append(domain)
write_to_file(warninglist, dst)
def process(url, dst):
warninglist = {
'name':
'List of disposable email domains',
'version':
get_version(),
'description':
'List of disposable email domains',
'list':
process_stream(url),
'type':
'substring',
'matching_attributes': [
"email-src", "email-dst", "whois-registrant-email", "domain|ip",
"dns-soa-email"
]
}
write_to_file(warninglist, dst)
def process(url, dst):
warninglist = {
'name': 'List of known Wikimedia address ranges',
'version': get_version(),
'description':
'Wikimedia address ranges (http://noc.wikimedia.org/conf/reverse-proxy.php.txt)',
'type': 'cidr',
'list': [],
'matching_attributes': ["ip-src", "ip-dst", "domain|ip"]
}
matched = re.findall(r'\'(.*?)\'',
codecs.decode(download(url).content, 'UTF-8'))
for ip in matched:
try:
ipaddress.ip_network(ip)
warninglist['list'].append(ip)
except ValueError:
pass
write_to_file(warninglist, dst)
def process(file, dst):
with open(get_abspath_source_file(file), 'r') as json_file:
amazon_aws_ip_list = json.load(json_file)
l = []
for prefix in amazon_aws_ip_list['prefixes']:
l.append(prefix['ip_prefix'])
for prefix in amazon_aws_ip_list['ipv6_prefixes']:
l.append(prefix['ipv6_prefix'])
warninglist = {
'name': 'List of known Amazon AWS IP address ranges',
'version': get_version(),
'description':
'Amazon AWS IP address ranges (https://ip-ranges.amazonaws.com/ip-ranges.json)',
'type': 'cidr',
'list': l,
'matching_attributes': ["ip-src", "ip-dst", "domain|ip"]
}
write_to_file(warninglist, dst)
def process(files, dst):
warninglist = {
'name': "List of known Stackpath CDN IP ranges",
'version': get_version(),
'description': "List of known Stackpath (Highwinds) CDN IP ranges (https://support.stackpath.com/hc/en-us/articles/360001091666-Whitelist-CDN-WAF-IP-Blocks)",
'type': "cidr",
'list': [],
'matching_attributes': ["ip-dst", "ip-src", "domain|ip"]
}
for file in files:
with open(get_abspath_source_file(file), 'r') as f:
ips = f.readlines()
for ip in ips:
iptoadd = ip.strip()
try:
ipaddress.ip_network(ip.strip())
except ValueError as err:# if it's host given strip to the subnet
iptoadd = str(ipaddress.IPv6Interface(ip.strip()).ip)
warninglist['list'].append(iptoadd)
write_to_file(warninglist, dst)
def process(file, dst):
with zipfile.ZipFile(file, 'r') as alexa_lists:
for name in alexa_lists.namelist():
if name == "top-1m.csv":
with alexa_lists.open(name) as top:
top1000 = top.readlines()[:1000]
else:
continue
warninglist = {
'description': "Event contains one or more entries from the top 1000 of the most used website (Alexa).",
'version': get_version(),
'name': "Top 1000 website from Alexa",
'type': 'hostname',
'list': [],
'matching_attributes': ['hostname', 'domain', 'url', 'domain|ip']
}
for site in top1000:
v = site.decode('UTF-8').split(',')[1]
warninglist['list'].append(v.rstrip())
write_to_file(warninglist, dst)
networks = set()
asn_to_fetch = []
for asn in search_result["data"]["asns"]:
if is_akamai(asn):
asn_to_fetch.append(asn["asn"])
for prefix in search_result["data"]["ipv4_prefixes"]:
if is_akamai(prefix):
networks.add(prefix["prefix"])
for prefix in search_result["data"]["ipv6_prefixes"]:
if is_akamai(prefix):
networks.add(prefix["prefix"])
for asn in asn_to_fetch:
try:
networks.update(get_networks_for_asn(asn))
except Exception as e:
print(str(e))
warninglist = {
'name': 'List of known Akamai IP ranges',
'version': get_version(),
'description': 'Akamai IP ranges from BGP search',
'type': 'cidr',
'list': consolidate_networks(networks),
'matching_attributes': ["ip-src", "ip-dst", "domain|ip"]
}
write_to_file(warninglist, "akamai")
def generate(data_list, dst, warninglist):
warninglist['version'] = get_version()
warninglist['list'] = data_list
write_to_file(warninglist, dst)
