Sunday, January 10, 2010

XSS filtering function in PHP

$data = str_replace(array('&','<','>'), array('&amp;','&lt;','&gt;'), $data);
$data = preg_replace('/(&#*\w+)[\x00-\x20]+;/u', '$1;', $data);
$data = preg_replace('/(&#x*[0-9A-F]+);*/iu', '$1;', $data);
$data = html_entity_decode($data, ENT_COMPAT, 'UTF-8');

// Remove any attribute starting with "on" or xmlns
$data = preg_replace('#(<[^>]+?[\x00-\x20"\'])(?:on|xmlns)[^>]*+>#iu', '$1>', $data);

// Remove javascript: and vbscript: protocols
$data = preg_replace('#([a-z]*)[\x00-\x20]*=[\x00-\x20]*([`\'"]*)[\x00-\x20]*j[\x00-\x20]*a[\x00-\x20]*v[\x00-\x20]*a[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iu', '$1=$2nojavascript...', $data);
$data = preg_replace('#([a-z]*)[\x00-\x20]*=([\'"]*)[\x00-\x20]*v[\x00-\x20]*b[\x00-\x20]*s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:#iu', '$1=$2novbscript...', $data);
$data = preg_replace('#([a-z]*)[\x00-\x20]*=([\'"]*)[\x00-\x20]*-moz-binding[\x00-\x20]*:#u', '$1=$2nomozbinding...', $data);

// Only works in IE: 
$data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?expression[\x00-\x20]*\([^>]*+>#i', '$1>', $data);
$data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?behaviour[\x00-\x20]*\([^>]*+>#i', '$1>', $data);
$data = preg_replace('#(<[^>]+?)style[\x00-\x20]*=[\x00-\x20]*[`\'"]*.*?s[\x00-\x20]*c[\x00-\x20]*r[\x00-\x20]*i[\x00-\x20]*p[\x00-\x20]*t[\x00-\x20]*:*[^>]*+>#iu', '$1>', $data);

// Remove namespaced elements (we do not need them)
$data = preg_replace('#]*+>#i', '', $data);

do
{
        // Remove really unwanted tags
        $old_data = $data;
        $data = preg_replace('#]*+>#i', '', $data);
}
while ($old_data !== $data);

// we are done...
return $data;
}

No comments:

Post a Comment