class WebServerValidator(metaclass=Singleton):
def __init__(self):
self.request_handler = RequestHandler()
def validate_target_webserver(self, host):
try:
self.request_handler.send(
timeout=20,
url="{}://{}:{}".format(
host.protocol,
host.target,
host.port
)
)
return True
except (ConnectionError, TooManyRedirects, HTTPError, RequestHandlerException):
raise WebServerValidatorException
class URLFuzzer:
def __init__(self,
host,
ignored_response_codes,
num_threads,
wordlist,
follow_redirects=False):
self.target = host.target
self.ignored_error_codes = ignored_response_codes
self.proto = host.protocol
self.port = host.port
self.num_threads = num_threads
self.wordlist = wordlist
self.follow_redirects = follow_redirects
self.request_handler = RequestHandler(
) # Will get the single, already initiated instance
self.logger = None
def _log_response(self, code, url, headers):
if 300 > code >= 200:
color = COLOR.GREEN
elif 400 > code >= 300:
color = COLOR.BLUE
url += " redirects to {}".format(headers.get("Location"))
elif 510 > code >= 400:
color = COLOR.RED
else:
color = COLOR.RESET
self.logger.info("{}[{}]{} {}".format(color, code, COLOR.RESET, url))
def _fetch(self, uri, sub_domain=False):
"""
Send a HEAD request to URL and print response code if it's not in ignored_error_codes
:param uri: URI to fuzz
:param sub_domain: If True, build destination URL with {URL}.{HOST} else {HOST}/{URL}
"""
if not sub_domain:
if self.port != 80 and self.port != 443:
url = "{}://{}:{}/{}".format(self.proto, self.target,
self.port, uri)
else:
url = "{}://{}/{}".format(self.proto, self.target, uri)
else:
if self.port != 80 and self.port != 443:
url = "{}://{}.{}:{}".format(self.proto, uri, self.target,
self.port)
else:
url = "{}://{}.{}".format(self.proto, uri, self.target)
try:
res = self.request_handler.send(
"HEAD", url=url, allow_redirects=self.follow_redirects)
if res.status_code not in self.ignored_error_codes:
self._log_response(res.status_code, url, res.headers)
except (AttributeError, RequestHandlerException):
# res is None or another error occurred
pass
def get_log_file_path(self, path):
if path:
log_file = path
else:
log_file = "{}/url_fuzz.txt".format(self.target)
return Logger(HelpUtilities.get_output_path(log_file))
async def fuzz_all(self, sub_domain=False, log_file_path=None):
"""
Create a pool of threads, read the wordlist and invoke fuzz_all.
Should be run in an event loop.
:param sub_domain: Indicate if this is subdomain enumeration or URL busting
:param log_file_path: Log subdomain enum results to this path.
"""
self.logger = self.get_log_file_path(log_file_path)
try:
with open(self.wordlist, "r") as file:
fuzzlist = file.readlines()
fuzzlist = [x.replace("\n", "") for x in fuzzlist]
except FileNotFoundError:
raise FuzzerException(
"Cannot read URL list from {}. Will not perform Fuzzing".
format(self.wordlist))
self.logger.info("{} Fuzzing from {}".format(COLORED_COMBOS.INFO,
self.wordlist))
pool = ThreadPool(self.num_threads)
pool.map(partial(self._fetch, sub_domain=sub_domain), fuzzlist)
class WAF:
def __init__(self, host):
self.host = host
self.cnames = host.dns_results.get('CNAME')
self.request_handler = RequestHandler()
self.web_server_validator = WebServerValidator()
self.waf_present = False
self.waf_cname_map = {
"incapdns": "Incapsula",
"edgekey": "Akamai",
"akamai": "Akamai",
"edgesuite": "Akamai",
"distil": "Distil Networks",
"cloudfront": "CloudFront",
"netdna-cdn": "MaxCDN"
}
self.waf_app_method_map = {
"CloudFront": WAFApplicationMethods.detect_cloudfront,
"Cloudflare": WAFApplicationMethods.detect_cloudflare,
"Incapsula": WAFApplicationMethods.detect_incapsula,
"MaxCDN": WAFApplicationMethods.detect_maxcdn,
"Edgecast": WAFApplicationMethods.detect_edgecast,
"Distil Networks": WAFApplicationMethods.detect_distil
}
log_file = HelpUtilities.get_output_path("{}/WAF.txt".format(
self.host.target))
self.logger = Logger(log_file)
def _waf_detected(self, name):
self.logger.info(
"{} Detected WAF presence in web application: {}{}{}".format(
COLORED_COMBOS.BAD, COLOR.RED, name, COLOR.RESET))
self.waf_present = True
def _detect_by_cname(self):
for waf in self.waf_cname_map:
if any(waf in str(cname) for cname in self.cnames):
self.logger.info(
"{} Detected WAF presence in CNAME: {}{}{}".format(
COLORED_COMBOS.BAD, COLOR.RED,
self.waf_cname_map.get(waf), COLOR.RESET))
self.waf_present = True
def _detect_by_application(self):
try:
response = self.request_handler.send(
"HEAD",
timeout=20,
allow_redirects=True,
url="{}://{}:{}".format(self.host.protocol, self.host.target,
self.host.port))
for waf, method in self.waf_app_method_map.items():
result = method(response.headers)
if result:
self._waf_detected(waf)
except (ConnectionError, TooManyRedirects) as e:
raise WAFException("Couldn't get response from server.\n"
"Caused due to exception: {}".format(str(e)))
async def detect(self):
self.logger.info("{} Trying to detect WAF presence in {}".format(
COLORED_COMBOS.INFO, self.host))
if self.cnames:
self._detect_by_cname()
try:
self.web_server_validator.validate_target_webserver(self.host)
self._detect_by_application()
if not self.waf_present:
self.logger.info(
"{} Did not detect WAF presence in target".format(
COLORED_COMBOS.GOOD))
except WebServerValidatorException:
self.logger.info(
"{} Target does not seem to have an active web server on port: {}\n"
"No WAF could be detected on an application level.".format(
COLORED_COMBOS.WARNING, self.host.port))
class SubDomainEnumerator:
def __init__(self, host, sans, domain_list, ignored_response_codes,
num_threads, follow_redirects, bruteforce_subdomains):
self.host = host
self.target = host.target
self.sans = sans
self.domain_list = domain_list
self.ignored_error_codes = ignored_response_codes
self.num_threads = num_threads
self.follow_redirects = follow_redirects
self.bruteforce_subdomains = bruteforce_subdomains
self.request_handler = RequestHandler()
self.sub_domains = set()
log_file = HelpUtilities.get_output_path("{}/subdomains.txt".format(
self.target))
self.logger = Logger(log_file)
async def run(self):
self.logger.info("\n{} Enumerating Subdomains".format(
COLORED_COMBOS.INFO))
if self.sans:
self.find_subdomains_in_sans()
self.google_dork()
if self.bruteforce_subdomains:
await self.bruteforce()
self.logger.info("\n{} Done enumerating Subdomains".format(
COLORED_COMBOS.INFO))
def find_subdomains_in_sans(self):
"""Looks for different TLDs as well as different sub-domains in SAN list"""
self.logger.info("{} Trying to find Subdomains in SANs list".format(
COLORED_COMBOS.INFO))
if self.host.naked:
domain = self.host.naked
tld_less = domain.split(".")[0]
else:
domain = self.host.target.split(".")
tld_less = domain[1]
domain = ".".join(domain[1:])
for san in self.sans:
if (tld_less in san or domain in san) and self.target != san:
self.logger.info("{} Subdomain detected: {}".format(
COLORED_COMBOS.GOOD, san))
def google_dork(self):
self.logger.info("{} Trying to discover subdomains in Google".format(
COLORED_COMBOS.INFO))
page = self.request_handler.send(
"GET",
url="https://www.google.com/search?q=site:{}&num=100".format(
self.target))
soup = BeautifulSoup(page.text, "lxml")
results = set(re.findall(r"\w+\.{}".format(self.target), soup.text))
for subdomain in results:
if "www." not in subdomain:
self.logger.info(
"{} Detected subdomain through Google dorking: {}".format(
COLORED_COMBOS.GOOD, subdomain))
async def bruteforce(self):
path = "{}/subdomain_fuzz.txt".format(self.host.target)
# If a naked domain exists, use it
if self.host.naked:
self.host.target = self.host.naked
self.logger.info("{} Bruteforcing subdomains".format(
COLORED_COMBOS.INFO))
sub_domain_fuzzer = URLFuzzer(
host=self.host,
wordlist=self.domain_list,
num_threads=self.num_threads,
ignored_response_codes=self.ignored_error_codes,
follow_redirects=self.follow_redirects)
await sub_domain_fuzzer.fuzz_all(sub_domain=True, log_file_path=path)
class WebApplicationScanner:
def __init__(self, host):
self.host = host
self.request_handler = RequestHandler()
self.web_server_validator = WebServerValidator()
self.web_scan_results = []
self.headers = None
self.robots = None
log_file = HelpUtilities.get_output_path("{}/web_scan.txt".format(self.host.target))
self.target_dir = "/".join(log_file.split("/")[:-1])
self.logger = Logger(log_file)
def _detect_cms(self, tries=0):
"""
Detect CMS using whatcms.org.
Has a re-try mechanism because false negatives may occur
:param tries: Count of tries for CMS discovery
"""
page = requests.get("https://whatcms.org/?s={}".format(self.host.target))
soup = BeautifulSoup(page.text, "lxml")
found = soup.select(".panel.panel-success")
if found:
try:
cms = [a for a in soup.select("a") if "/c/" in a.get("href")][0]
self.logger.info("{} CMS detected: target is using {}{}{}".format(
COLORED_COMBOS.GOOD, COLOR.GREEN, cms.get("title"), COLOR.RESET))
except IndexError:
if tries >= 4:
return
else:
self._detect_cms(tries=tries + 1)
else:
if tries >= 4:
return
else:
self._detect_cms(tries=tries + 1)
def _cookie_info(self, jar):
for cookie in jar:
key = cookie.__dict__.get("name")
value = cookie.__dict__.get("value")
domain = cookie.__dict__.get("domain")
secure = cookie.__dict__.get("secure")
try:
if domain in self.host.target or self.host.target in domain:
if not secure:
self.logger.info(
"%s Found cookie without secure flag: {%s: %s}" % (COLORED_COMBOS.GOOD, key, value)
)
except TypeError:
continue
def _server_info(self):
if self.headers.get("server"):
self.logger.info("{} Web server detected: {}{}{}".format(
COLORED_COMBOS.GOOD, COLOR.GREEN, self.headers.get("server"), COLOR.RESET))
def _x_powered_by(self):
if self.headers.get("X-Powered-By"):
self.logger.info("{} X-Powered-By header detected: {}{}{}".format(
COLORED_COMBOS.GOOD, COLOR.GREEN, self.headers.get("X-Powered-By"), COLOR.RESET))
def _anti_clickjacking(self):
if not self.headers.get("X-Frame-Options"):
self.logger.info(
"{} X-Frame-Options header not detected - target might be vulnerable to clickjacking".format(
COLORED_COMBOS.GOOD)
)
def _xss_protection(self):
xss_header = self.headers.get("X-XSS-PROTECTION")
if xss_header and "1" in xss_header:
self.logger.info("{} Found X-XSS-PROTECTION header".format(COLORED_COMBOS.BAD))
def _cors_wildcard(self):
if self.headers.get("Access-Control-Allow-Origin") == "*":
self.logger.info("{} CORS wildcard detected".format(COLORED_COMBOS.GOOD))
def _robots(self):
res = self.request_handler.send(
"GET",
url="{}://{}:{}/robots.txt".format(
self.host.protocol,
self.host.target,
self.host.port
)
)
if res.status_code != 404 and res.text and "<!DOCTYPE html>" not in res.text:
self.logger.info("{} Found robots.txt".format(COLORED_COMBOS.GOOD))
with open("{}/robots.txt".format(self.target_dir), "w") as file:
file.write(res.text)
def _sitemap(self):
res = self.request_handler.send(
"GET",
url="{}://{}:{}/sitemap.xml".format(
self.host.protocol,
self.host.target,
self.host.port
)
)
if res.status_code != 404 and res.text and "<!DOCTYPE html>" not in res.text:
self.logger.info("{} Found sitemap.xml".format(COLORED_COMBOS.GOOD))
with open("{}/sitemap.xml".format(self.target_dir), "w") as file:
file.write(res.text)
def get_web_application_info(self):
session = self.request_handler.get_new_session()
try:
with session:
# Test if target is serving HTTP requests
response = session.get(
timeout=20,
url="{}://{}:{}".format(
self.host.protocol,
self.host.target,
self.host.port
)
)
self.headers = response.headers
self._detect_cms()
self._robots()
self._sitemap()
self._server_info()
self._x_powered_by()
self._cors_wildcard()
self._xss_protection()
self._anti_clickjacking()
self._cookie_info(session.cookies)
except (ConnectionError, TooManyRedirects) as e:
raise WebAppScannerException("Couldn't get response from server.\n"
"Caused due to exception: {}".format(str(e)))
async def run_scan(self):
self.logger.info("{} Trying to collect {} web application data".format(COLORED_COMBOS.INFO, self.host))
try:
self.web_server_validator.validate_target_webserver(self.host)
self.get_web_application_info()
except WebServerValidatorException:
self.logger.info(
"{} Target does not seem to have an active web server on port: {}. "
"No web application data will be gathered.".format(COLORED_COMBOS.WARNING, self.host.port))
return