This file is indexed.

/usr/share/w3af/plugins/grep/findComments.py is in w3af-console 1.1svn5547-1.1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
# coding: utf-8

'''
findComments.py

Copyright 2006 Andres Riancho

This file is part of w3af, w3af.sourceforge.net .

w3af is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation version 2 of the License.

w3af is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with w3af; if not, write to the Free Software
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA

'''
from __future__ import with_statement

import core.controllers.outputManager as om
import core.data.parsers.dpCache as dpCache
from core.data.esmre.multi_in import multi_in

# options
from core.data.options.option import option
from core.data.options.optionList import optionList

from core.controllers.basePlugin.baseGrepPlugin import baseGrepPlugin
from core.controllers.w3afException import w3afException

from core.controllers.coreHelpers.fingerprint_404 import is_404
import core.data.kb.knowledgeBase as kb
import core.data.kb.info as info

import re


class findComments(baseGrepPlugin):
    '''
    Find HTML comments.
      
    @author: Andres Riancho ( andres.riancho@gmail.com )
    '''
    
    HTML_RE = re.compile('<[a-zA-Z]*.*?>.*?</[a-zA-Z]>')

    INTERESTING_WORDS = (
        'user', 'pass', 'xxx', 'fix', 'bug', 'broken', 'oops', 'hack',
        'caution', 'todo', 'note', 'warning', '!!!', '???', 'shit',
        'stupid', 'tonto', 'porqueria', 'ciudado', 'usuario', 'contrase',
        'puta', 'secret', '@', 'email','security','captcha', 'pinga',
        'cojones',
        # some in Portuguese
        'banco', 'bradesco', 'itau', 'visa', 'bancoreal', u'transfêrencia',
        u'depósito', u'cartão', u'crédito', 'dados pessoais'
    )
    
    _multi_in = multi_in( INTERESTING_WORDS )

    def __init__(self):
        baseGrepPlugin.__init__(self)

        # Internal variables
        self._comments = {}
        self._already_reported_interesting = []
        
        # User configurations
        self._search404 = False
        
    def grep(self, request, response):
        '''
        Plugin entry point, parse those comments!
        
        @parameter request: The HTTP request object.
        @parameter response: The HTTP response object
        @return: None
        '''
        if response.is_text_or_html() and (not is_404( response ) or self._search404):
            try:
                dp = dpCache.dpc.getDocumentParserFor( response )
            except w3afException:
                return
            else:
                for comment in dp.getComments():
                    # These next two lines fix this issue:
                    # audit.ssi + grep.findComments + web app with XSS = false positive
                    if request.sent( comment ):
                        continue
                    
                    # show nice comments ;)
                    comment = comment.strip()
                    
                    if self._is_new( comment, response):
                        
                        self._interesting_word( comment, request, response )
                        self._html_in_comment( comment, request, response )

    def _interesting_word(self, comment, request, response):
        '''
        Find interesting words in HTML comments
        '''
        comment = comment.lower()
        for word in self._multi_in.query( response.body ):                    
            if (word, response.getURL()) not in self._already_reported_interesting:
                i = info.info()
                i.setPluginName(self.getName())
                i.setName('HTML comment with "' + word + '" inside')
                msg = 'A comment with the string "' + word + '" was found in: "'
                msg += response.getURL() + '". This could be interesting.'
                i.setDesc( msg )
                i.setId( response.id )
                i.setDc( request.getDc )
                i.setURI( response.getURI() )
                i.addToHighlight( word )
                kb.kb.append( self, 'interestingComments', i )
                om.out.information( i.getDesc() )
                self._already_reported_interesting.append( ( word, response.getURL() ) )

    def _html_in_comment(self, comment, request, response):                    
        '''
        Find HTML code in HTML comments
        '''
        html_in_comment = self.HTML_RE.search( comment )
        if html_in_comment and \
        ( comment, response.getURL() ) not in self._already_reported_interesting:
            # There is HTML code in the comment.
            i = info.info()
            i.setPluginName(self.getName())
            i.setName('HTML comment contains HTML code')
            comment = comment.replace('\n','')
            comment = comment.replace('\r','')
            desc = 'A comment with the string "' +comment + '" was found in: "'
            desc += response.getURL() + '" . This could be interesting.'
            i.setDesc( desc )
            i.setId( response.id )
            i.setDc( request.getDc )
            i.setURI( response.getURI() )
            i.addToHighlight( html_in_comment.group(0) )
            kb.kb.append( self, 'htmlCommentsHideHtml', i )
            om.out.information( i.getDesc() )
            self._already_reported_interesting.append( ( comment, response.getURL() ) )
                            
    def _is_new(self, comment, response):
        '''
        Make sure that we perform a thread safe check on the self._comments dict,
        in order to avoid duplicates.
        '''
        with self._plugin_lock:
            if comment not in self._comments.keys():
                self._comments[ comment ] = [ (response.getURL(), response.id), ]
                return True
            else:
                if response.getURL() not in [ x[0] for x in self._comments[ comment ] ]:
                    self._comments[ comment ].append( (response.getURL(), response.id) )
                    return True
        
        return False        
    
    def setOptions( self, optionsMap ):
        self._search404 = optionsMap['search404'].getValue()
    
    def getOptions( self ):
        '''
        @return: A list of option objects for this plugin.
        '''
        d1 = 'Search for HTML comments in 404 pages.'
        o1 = option('search404', self._search404, d1, 'boolean')
        
        ol = optionList()
        ol.add(o1)
        return ol

    def end(self):
        '''
        This method is called when the plugin wont be used anymore.
        @return: None
        '''
        inform = []
        for comment in self._comments.keys():
            urls_with_this_comment = self._comments[comment]
            stick_comment = ' '.join(comment.split())
            if len(stick_comment) > 40:
                msg = 'A comment with the string "%s..." (and %s more bytes) was found on these URL(s):'
                om.out.information( msg % (stick_comment[:40], str(len(stick_comment) - 40) ))
            else:
                msg = 'A comment containing "%s" was found on these URL(s):' % (stick_comment)
                om.out.information( msg )
             
            for url , request_id in urls_with_this_comment:
                inform.append('- ' + url + ' (request with id: '+str(request_id)+')' )
        
            inform.sort()
            for i in inform:
                om.out.information( i )

    def getPluginDeps( self ):
        '''
        @return: A list with the names of the plugins that should be run before the
        current one.
        '''
        return []
    
    def getLongDesc( self ):
        '''
        @return: A DETAILED description of the plugin functions and features.
        '''
        return '''
        This plugin greps every page for HTML comments, special comments like the ones containing
        the words "password" or "user" are specially reported.
        '''