Multiple updates -> 3.1.3

- Removed browser engine emulation (closes #220, closes #217, closes #200 ) 
- Fixed a few bugs
- Added a plugin to scan for outdated JS libraries
- Improved crawling and DOM scanning

Author: s0md3v

.travis.yml

@@ -1,7 +1,5 @@
 language: python
 cache: pip
-addons:
-  firefox: "45.4.0esr"
 os:
   - linux
 python:
@@ -10,11 +8,6 @@ install:
   - pip install -r requirements.txt
   - pip install flake8
 before_script:
-  # download and extract geckodrive to /usr/local/bin
-  - wget https://github.com/mozilla/geckodriver/releases/download/v0.23.0/geckodriver-v0.23.0-linux64.tar.gz
-  - mkdir geckodriver
-  - tar -xzf geckodriver-v0.23.0-linux64.tar.gz -C geckodriver
-  - export PATH=$PATH:$PWD/geckodriver  # stop the build if there are Python syntax errors or undefined names
   - flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics
   # exit-zero treats all errors as warnings.  The GitHub editor is 127 chars wide
   - flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics

CHANGELOG.md

@@ -1,3 +1,9 @@
+### 3.1.3
+- Removed browser engine emulation
+- Fixed a few bugs
+- Added a plugin to scan for outdated JS libraries
+- Improved crawling and DOM scanning
+
 ### 3.1.2
 - Fixed POST data handling
 - Support for JSON POST data

README.md

@@ -49,7 +49,7 @@ Apart from that, XSStrike has crawling, fuzzing, parameter discovery, WAF detect
 - Context analysis
 - Configurable core
 - WAF detection & evasion
-- Browser engine integration for zero false positive rate
+- Outdated JS lib scanning
 - Intelligent payload generator
 - Handmade HTML & JavaScript parser
 - Powerful fuzzing engine
@@ -65,7 +65,6 @@ Apart from that, XSStrike has crawling, fuzzing, parameter discovery, WAF detect
 - [Compatibility & Dependencies](https://github.com/s0md3v/XSStrike/wiki/Compatibility-&-Dependencies)
 
 ### FAQ
-- [There's some error related to `geckodriver`.](https://github.com/s0md3v/XSStrike/wiki/FAQ#theres-some-error-related-to-geckodriver)
 - [It says fuzzywuzzy isn't installed but it is.](https://github.com/s0md3v/XSStrike/wiki/FAQ#it-says-fuzzywuzzy-is-not-installed-but-its)
 - [What's up with Blind XSS?](https://github.com/s0md3v/XSStrike/wiki/FAQ#whats-up-with-blind-xss)
 - [Why XSStrike boasts that it is the most advanced XSS detection suite?](https://github.com/s0md3v/XSStrike/wiki/FAQ#why-xsstrike-boasts-that-it-is-the-most-advanced-xss-detection-suite)
@@ -103,4 +102,5 @@ Ways to contribute
 
 Licensed under the GNU GPLv3, see [LICENSE](LICENSE) for more information.
 
-The WAF signatures in `/db/wafSignatures.json` are taken & modified from [sqlmap](https://github.com/sqlmapproject/sqlmap). I extracted them from sqlmap's waf detection modules which can found [here](https://github.com/sqlmapproject/sqlmap/blob/master/waf/) and converted them to JSON.
+The WAF signatures in `/db/wafSignatures.json` are taken & modified from [sqlmap](https://github.com/sqlmapproject/sqlmap). I extracted them from sqlmap's waf detection modules which can found [here](https://github.com/sqlmapproject/sqlmap/blob/master/waf/) and converted them to JSON.\
+`/plugins/retireJS.py` is a modified version of [retirejslib](https://github.com/FallibleInc/retirejslib/).

core/browserEngine.py

@@ -1,4 +1,4 @@
-changes = '''better dom xss scanning;add headers from command line;many bug fixes'''
+changes = '''Removed browser engine emulation;Fixed a few bugs;Added a plugin to scan for outdated JS libraries;Improved crawling and DOM scanning'''
 globalVariables = {}  # it holds variables during runtime for collaboration across modules
 
 defaultEditor = 'nano'

core/config.py

@@ -7,7 +7,7 @@ def dom(response):
     highlighted = []
     sources = r'''document\.(URL|documentURI|URLUnencoded|baseURI|cookie|referrer)|location\.(href|search|hash|pathname)|window\.name|history\.(pushState|replaceState)(local|session)Storage'''
     sinks = r'''eval|evaluate|execCommand|assign|navigate|getResponseHeaderopen|showModalDialog|Function|set(Timeout|Interval|Immediate)|execScript|crypto.generateCRMFRequest|ScriptElement\.(src|text|textContent|innerText)|.*?\.onEventName|document\.(write|writeln)|.*?\.innerHTML|Range\.createContextualFragment|(document|window)\.location'''
-    scripts = re.findall(r'(?i)(?s)<scrip[^>]*(.*?)</script>', response)
+    scripts = re.findall(r'(?i)(?s)<script[^>]*>(.*?)</script>', response)
     for script in scripts:
         script = script.split('\n')
         num = 1

core/dom.py

@@ -3,6 +3,7 @@
 from urllib.parse import urlparse
 
 
+from plugins.retireJs import retireJs
 from core.utils import getUrl, getParams
 from core.requester import requester
 from core.zetanize import zetanize
@@ -36,6 +37,7 @@ def rec(target):
                 inps.append({'name': name, 'value': value})
             forms.append({0: {'action': url, 'method': 'get', 'inputs': inps}})
         response = requester(url, params, headers, True, delay, timeout).text
+        retireJs(url, response)
         forms.append(zetanize(response))
         matches = findall(r'<[aA].*href=["\']{0,1}(.*?)["\']', response)
         for link in matches:  # iterate over the matches
@@ -53,9 +55,11 @@ def rec(target):
                 storage.add(main_url + '/' + link)
     for x in range(level):
         urls = storage - processed  # urls to crawl = all urls - urls that have been crawled
+        # for url in urls:
+        #     rec(url)
         threadpool = concurrent.futures.ThreadPoolExecutor(
             max_workers=threadCount)
         futures = (threadpool.submit(rec, url) for url in urls)
-        for i, _ in enumerate(concurrent.futures.as_completed(futures)):
+        for i in concurrent.futures.as_completed(futures):
             pass
     return [forms, processed]

core/photon.py

@@ -5,8 +5,7 @@
 import warnings
 
 import core.config
-from core.config import globalVariables
-from core.utils import converter
+from core.utils import converter, getVar
 from core.log import setup_logger
 
 logger = setup_logger(__name__)
@@ -15,9 +14,9 @@
 
 
 def requester(url, data, headers, GET, delay, timeout):
-    if core.config.globalVariables['jsonData']:
+    if getVar('jsonData'):
         data = converter(data)
-    elif core.config.globalVariables['path']:
+    elif getVar('path'):
         url = converter(data, url)
         data = []
         GET, POST = True, False
@@ -37,7 +36,7 @@ def requester(url, data, headers, GET, delay, timeout):
         if GET:
             response = requests.get(url, params=data, headers=headers,
                                     timeout=timeout, verify=False, proxies=core.config.proxies)
-        elif core.config.globalVariables['jsonData']:
+        elif getVar('jsonData'):
             response = requests.get(url, json=data, headers=headers,
                                     timeout=timeout, verify=False, proxies=core.config.proxies)
         else:

core/requester.py

@@ -163,7 +163,7 @@ def getParams(url, data, GET):
         if data[:1] == '?':
             data = data[1:]
     elif data:
-        if core.config.globalVariables['jsonData'] or core.config.globalVariables['path']:
+        if getVar('jsonData') or getVar('path'):
             params = data
         else:
             try:
@@ -197,6 +197,51 @@ def writer(obj, path):
 
 def reader(path):
     with open(path, 'r') as f:
-        result = [line.strip(
+        result = [line.rstrip(
                     '\n').encode('utf-8').decode('utf-8') for line in f]
     return result
+
+def js_extractor(response):
+    """Extract js files from the response body"""
+    scripts = []
+    matches = re.findall(r'<(?:script|SCRIPT).*?(?:src|SRC)=([^\s>]+)', response)
+    for match in matches:
+        match = match.replace('\'', '').replace('"', '').replace('`', '')
+        scripts.append(match)
+    return scripts
+
+
+def handle_anchor(parent_url, url):
+    if parent_url.count('/') > 2:
+        replacable = re.search(r'/[^/]*?$', parent_url).group()
+        if replacable != '/':
+            parent_url = parent_url.replace(replacable, '')
+    scheme = urlparse(parent_url).scheme
+    if url[:4] == 'http':
+        return url
+    elif url[:2] == '//':
+        return scheme + ':' + url
+    elif url[:1] == '/':
+        return parent_url + url
+    else:
+        if parent_url.endswith('/') or url.startswith('/'):
+            return parent_url + url
+        else:
+            return parent_url + '/' + url
+
+
+def deJSON(data):
+    return data.replace('\\\\', '\\')
+
+
+def getVar(name):
+    return core.config.globalVariables[name]
+
+def updateVar(name, data, mode=None):
+    if mode:
+        if mode == 'append':
+            core.config.globalVariables[name].append(data)
+        elif mode == 'add':
+            core.config.globalVariables[name].add(data)
+    else:
+        core.config.globalVariables[name] = data