1 function RemoveXSS($val) {
2 // remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed
3 // this prevents some character re-spacing such as <java\0script>
4 // note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
5 $val = preg_replace('/([\x00-\x08,\x0b-\x0c,\x0e-\x19])/', '', $val);
6 // straight replacements, the user should never need these since they're normal characters
7 // this prevents like <IMG SRC=@avascript:alert('XSS')>
8 $search = 'abcdefghijklmnopqrstuvwxyz';
9 $search .= 'ABCDEFGHIJKLMNOPQRSTUVWXYZ';
10 $search .= '1234567890!@#$%^&*()';
11 $search .= '~`";:?+/={}[]-_|\'\\';
12 for ($i = 0; $i < strlen($search); $i++) {
13 // ;? matches the ;, which is optional
14 // 0{0,7} matches any padded zeros, which are optional and go up to 8 chars
15
16 // @ @ search for the hex values
17 $val = preg_replace('/(&#[xX]0{0,8}'.dechex(ord($search[$i])).';?)/i', $search[$i], $val); // with a ;
18 // @ @ 0{0,7} matches '0' zero to seven times
19 $val = preg_replace('/(�{0,8}'.ord($search[$i]).';?)/', $search[$i], $val); // with a ;
20 }
21
22 // now the only remaining whitespace attacks are \t, \n, and \r
23 $ra1 = array('javascript', 'vbscript', 'expression', 'applet', 'meta', 'xml', 'blink', 'link', 'style', 'script', 'embed', 'object', 'iframe', 'frame', 'frameset', 'ilayer', 'layer', 'bgsound', 'title', 'base');
24 $ra2 = array('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');
25 $ra = array_merge($ra1, $ra2);
26
27 $found = true; // keep replacing as long as the previous round replaced something
28 while ($found == true) {
29 $val_before = $val;
30 for ($i = 0; $i < sizeof($ra); $i++) {
31 $pattern = '/';
32 for ($j = 0; $j < strlen($ra[$i]); $j++) {
33 if ($j > 0) {
34 $pattern .= '(';
35 $pattern .= '(&#[xX]0{0,8}([9ab]);)';
36 $pattern .= '|';
37 $pattern .= '|(�{0,8}([9|10|13]);)';
38 $pattern .= ')*';
39 }
40 $pattern .= $ra[$i][$j];
41 }
42 $pattern .= '/i';
43 $replacement = substr($ra[$i], 0, 2).'<x>'.substr($ra[$i], 2); // add in <> to nerf the tag
44 $val = preg_replace($pattern, $replacement, $val); // filter out the hex tags
45 if ($val_before == $val) {
46 // no replacements were made, so exit the loop
47 $found = false;
48 }
49 }
50 }
51 return $val;
52 }