3aeb4b0c6dbb91e08b9a580688c6cfcad55a7c79
[Packages/TYPO3.CMS.git] / typo3 / contrib / RemoveXSS / RemoveXSS.php
1 <?php
2 /**
3 * Usage: Run *every* variable passed in through it.
4 * The goal of this function is to be a generic function that can be used to
5 * parse almost any input and render it XSS safe. For more information on
6 * actual XSS attacks, check out http://ha.ckers.org/xss.html. Another
7 * excellent site is the XSS Database which details each attack and how it
8 * works.
9 *
10 * Used with permission by the author.
11 * URL: http://quickwired.com/smallprojects/php_xss_filter_function.php
12 *
13 * Check XSS attacks on http://ha.ckers.org/xss.html
14 *
15 * License:
16 * This code is public domain, you are free to do whatever you want with it,
17 * including adding it to your own project which can be under any license.
18 *
19 * @author Travis Puderbaugh <kallahar@quickwired.com>
20 * @author Jigal van Hemert <jigal@xs4all.nl>
21 * @package RemoveXSS
22 */
23 final class RemoveXSS {
24
25 /**
26 * Removes potential XSS code from an input string.
27 *
28 * Using an external class by Travis Puderbaugh <kallahar@quickwired.com>
29 *
30 * @param string Input string
31 * @param string replaceString for inserting in keywords (which destroyes the tags)
32 * @return string Input string with potential XSS code removed
33 */
34 public static function process($val, $replaceString = '<x>') {
35 // don't use empty $replaceString because then no XSS-remove will be done
36 if ($replaceString == '') {
37 $replaceString = '<x>';
38 }
39 // remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed
40 // this prevents some character re-spacing such as <java\0script>
41 // note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
42 $val = preg_replace('/([\x00-\x08][\x0b-\x0c][\x0e-\x19])/', '', $val);
43
44 // straight replacements, the user should never need these since they're normal characters
45 // this prevents like <IMG SRC=&#X40&#X61&#X76&#X61&#X73&#X63&#X72&#X69&#X70&#X74&#X3A&#X61&#X6C&#X65&#X72&#X74&#X28&#X27&#X58&#X53&#X53&#X27&#X29>
46 $searchHexEncodings = '/&#[xX]0{0,8}(21|22|23|24|25|26|27|28|29|2a|2b|2d|2f|30|31|32|33|34|35|36|37|38|39|3a|3b|3d|3f|40|41|42|43|44|45|46|47|48|49|4a|4b|4c|4d|4e|4f|50|51|52|53|54|55|56|57|58|59|5a|5b|5c|5d|5e|5f|60|61|62|63|64|65|66|67|68|69|6a|6b|6c|6d|6e|6f|70|71|72|73|74|75|76|77|78|79|7a|7b|7c|7d|7e);?/ie';
47 $searchUnicodeEncodings = '/&#0{0,8}(33|34|35|36|37|38|39|40|41|42|43|45|47|48|49|50|51|52|53|54|55|56|57|58|59|61|63|64|65|66|67|68|69|70|71|72|73|74|75|76|77|78|79|80|81|82|83|84|85|86|87|88|89|90|91|92|93|94|95|96|97|98|99|100|101|102|103|104|105|106|107|108|109|110|111|112|113|114|115|116|117|118|119|120|121|122|123|124|125|126);?/ie';
48 while (preg_match($searchHexEncodings, $val) || preg_match($searchUnicodeEncodings, $val)) {
49 $val = preg_replace($searchHexEncodings, "chr(hexdec('\\1'))", $val);
50 $val = preg_replace($searchUnicodeEncodings, "chr('\\1')", $val);
51 }
52
53 // now the only remaining whitespace attacks are \t, \n, and \r
54 $ra1 = array('javascript', 'vbscript', 'expression', 'applet', 'meta', 'xml', 'blink', 'link', 'style', 'script', 'embed', 'object', 'iframe', 'frame', 'frameset', 'ilayer', 'layer', 'bgsound', 'title', 'base', 'onabort', 'onactivate', 'onafterprint', 'onafterupdate', 'onbeforeactivate', 'onbeforecopy', 'onbeforecut', 'onbeforedeactivate', 'onbeforeeditfocus', 'onbeforepaste', 'onbeforeprint', 'onbeforeunload', 'onbeforeupdate', 'onblur', 'onbounce', 'oncellchange', 'onchange', 'onclick', 'oncontextmenu', 'oncontrolselect', 'oncopy', 'oncut', 'ondataavailable', 'ondatasetchanged', 'ondatasetcomplete', 'ondblclick', 'ondeactivate', 'ondrag', 'ondragend', 'ondragenter', 'ondragleave', 'ondragover', 'ondragstart', 'ondrop', 'onerror', 'onerrorupdate', 'onfilterchange', 'onfinish', 'onfocus', 'onfocusin', 'onfocusout', 'onhelp', 'onkeydown', 'onkeypress', 'onkeyup', 'onlayoutcomplete', 'onload', 'onlosecapture', 'onmousedown', 'onmouseenter', 'onmouseleave', 'onmousemove', 'onmouseout', 'onmouseover', 'onmouseup', 'onmousewheel', 'onmove', 'onmoveend', 'onmovestart', 'onpaste', 'onpropertychange', 'onreadystatechange', 'onreset', 'onresize', 'onresizeend', 'onresizestart', 'onrowenter', 'onrowexit', 'onrowsdelete', 'onrowsinserted', 'onscroll', 'onselect', 'onselectionchange', 'onselectstart', 'onstart', 'onstop', 'onsubmit', 'onunload');
55 $ra_tag = array('applet', 'meta', 'xml', 'blink', 'link', 'style', 'script', 'embed', 'object', 'iframe', 'frame', 'frameset', 'ilayer', 'layer', 'bgsound', 'title', 'base');
56 $ra_attribute = array('style', 'onabort', 'onactivate', 'onafterprint', 'onafterupdate', 'onbeforeactivate', 'onbeforecopy', 'onbeforecut', 'onbeforedeactivate', 'onbeforeeditfocus', 'onbeforepaste', 'onbeforeprint', 'onbeforeunload', 'onbeforeupdate', 'onblur', 'onbounce', 'oncellchange', 'onchange', 'onclick', 'oncontextmenu', 'oncontrolselect', 'oncopy', 'oncut', 'ondataavailable', 'ondatasetchanged', 'ondatasetcomplete', 'ondblclick', 'ondeactivate', 'ondrag', 'ondragend', 'ondragenter', 'ondragleave', 'ondragover', 'ondragstart', 'ondrop', 'onerror', 'onerrorupdate', 'onfilterchange', 'onfinish', 'onfocus', 'onfocusin', 'onfocusout', 'onhelp', 'onkeydown', 'onkeypress', 'onkeyup', 'onlayoutcomplete', 'onload', 'onlosecapture', 'onmousedown', 'onmouseenter', 'onmouseleave', 'onmousemove', 'onmouseout', 'onmouseover', 'onmouseup', 'onmousewheel', 'onmove', 'onmoveend', 'onmovestart', 'onpaste', 'onpropertychange', 'onreadystatechange', 'onreset', 'onresize', 'onresizeend', 'onresizestart', 'onrowenter', 'onrowexit', 'onrowsdelete', 'onrowsinserted', 'onscroll', 'onselect', 'onselectionchange', 'onselectstart', 'onstart', 'onstop', 'onsubmit', 'onunload');
57 $ra_protocol = array('javascript', 'vbscript', 'expression');
58
59 //remove the potential &#xxx; stuff for testing
60 $val2 = preg_replace('/(&#[xX]?0{0,8}(9|10|13|a|b);)*\s*/i', '', $val);
61 $ra = array();
62
63 foreach ($ra1 as $ra1word) {
64 //stripos is faster than the regular expressions used later
65 //and because the words we're looking for only have chars < 0x80
66 //we can use the non-multibyte safe version
67 if (stripos($val2, $ra1word ) !== false ) {
68 //keep list of potential words that were found
69 if (in_array($ra1word, $ra_protocol)) {
70 $ra[] = array($ra1word, 'ra_protocol');
71 }
72 if (in_array($ra1word, $ra_tag)) {
73 $ra[] = array($ra1word, 'ra_tag');
74 }
75 if (in_array($ra1word, $ra_attribute)) {
76 $ra[] = array($ra1word, 'ra_attribute');
77 }
78 //some keywords appear in more than one array
79 //these get multiple entries in $ra, each with the appropriate type
80 }
81 }
82 //only process potential words
83 if (count($ra) > 0) {
84 // keep replacing as long as the previous round replaced something
85 $found = TRUE;
86 while ($found == TRUE) {
87 $val_before = $val;
88 for ($i = 0; $i < sizeof($ra); $i++) {
89 $pattern = '';
90 for ($j = 0; $j < strlen($ra[$i][0]); $j++) {
91 if ($j > 0) {
92 $pattern .= '((&#[xX]0{0,8}([9ab]);)|(&#0{0,8}(9|10|13);)|\s)*';
93 }
94 $pattern .= $ra[$i][0][$j];
95 }
96 //handle each type a little different (extra conditions to prevent false positives a bit better)
97 switch ($ra[$i][1]) {
98 case 'ra_protocol':
99 //these take the form of e.g. 'javascript:'
100 $pattern .= '((&#[xX]0{0,8}([9ab]);)|(&#0{0,8}(9|10|13);)|\s)*(?=:)';
101 break;
102 case 'ra_tag':
103 //these take the form of e.g. '<SCRIPT[^\da-z] ....';
104 $pattern = '(?<=<)' . $pattern . '((&#[xX]0{0,8}([9ab]);)|(&#0{0,8}(9|10|13);)|\s)*(?=[^\da-z])';
105 break;
106 case 'ra_attribute':
107 //these take the form of e.g. 'onload=' Beware that a lot of characters are allowed
108 //between the attribute and the equal sign!
109 $pattern .= '[\s\!\#\$\%\&\(\)\*\~\+\-\_\.\,\:\;\?\@\[\/\|\\\\\]\^\`]*(?==)';
110 break;
111 }
112 $pattern = '/' . $pattern . '/i';
113 // add in <x> to nerf the tag
114 $replacement = substr_replace($ra[$i][0], $replaceString, 2, 0);
115 // filter out the hex tags
116 $val = preg_replace($pattern, $replacement, $val);
117 if ($val_before == $val) {
118 // no replacements were made, so exit the loop
119 $found = false;
120 }
121 }
122 }
123 }
124
125 return $val;
126 }
127 }
128
129 ?>