在我的應用程序中,我需要以字符串形式發送和接收HTML。我想保持安全,因此我需要檢查字符串中的dom元素是否匹配允許的標籤以及樣式聲明是否有效,以及是否沒有注入腳本。想到的第一件事當然是將字符串重新編排,但這很乏味,可能是錯誤的,肯定效率低下。第二個想法是用一種叫做XPath的,但即使我讀過關於MDN網站的一些材料,我仍然不知道如何實現此示例代碼:如何檢查HTML字符串是否安全?
const XPathResult = Components.interfaces.nsIDOMXPathResult;
const ALLOWED_TAGS = ['div', 'span', 'b', 'i', 'u', 'br', 'font', 'img'];
const ALLOWED_STYLES = ['font-weight', 'font-size', 'font-family', 'text-decoration', 'color', 'background-color'];
const ALLOWED_ATTRIBUTES = ['style', 'name'];
const XPATH_PART_TAGS = ALLOWED_TAGS.map(function (v) {
return "name() != '" + v + "' and name() != '" + v.toUpperCase() + "'"; // case insensitive
}).join(' and ');
const XPATH_PART_ATTRS = ALLOWED_ATTRIBUTES.map(function (v) {
return "name() != '" + v + "' and name() != '" + v.toUpperCase() + "'"; // case insensitive
}).join(' and ');
const XPATH_BAD_TAGS = "//*[(namespace-uri() != 'http://www.w3.org/1999/xhtml') or (" + XPATH_PART_TAGS + ")]";
const XPATH_BAD_ATTRIBUTES = "//@*[((namespace-uri() != 'http://www.w3.org/1999/xhtml') and (namespace-uri() != '')) or (" + XPATH_PART_ATTRS+ ")]";
const XPATH_STYLE = "//@*[name() = 'style']";
/**
* Checks if inline style definition is considered secure
*
* @param {String} styleValue value of style attribute
* @return bool
*/
function isStyleSecure(styleValue) {
var styles = styleValue.split(';'),
style,
name, value,
i, l;
for (i = 0, l = styles.length; i < l; i++) {
style = styles[i].trim();
if (style === '') {
continue;
}
style = style.split(':', 2);
if (style.length !== 2) {
return false;
}
name = style[0].trim().toLowerCase();
value = style[1].trim();
if (ALLOWED_STYLES.indexOf(name) === -1) {
return false;
}
}
return true;
}
/**
* Singleton that verifies if given XHTML document fragment is considered secure.
* Uses whitelist-based checks on tag names, attribute names and document namespaces.
*
* @class
* @namespace core.SecurityFilter.MessageSecurityFilter
*/
var MessageSecurityFilter = {
/**
* Checks if given document fragment is safe
*
* @param {nsIDOMElement} element root element of the XHTML document fragment to analyze
* @return {bool} true if fragment is safe, false otherwise
*/
isSecure: function SecurityFilter_isSecure(element) {
var document = element.ownerDocument,
result,
attr;
result = document.evaluate('//*', element, null, XPathResult.ANY_TYPE, null);
result = document.evaluate(XPATH_BAD_TAGS, element, null, XPathResult.ANY_TYPE, null);
if (result.iterateNext()) {
return false;
}
result = document.evaluate(XPATH_BAD_ATTRIBUTES, element, null, XPathResult.ANY_TYPE, null);
if ((attr = result.iterateNext())) {
return false;
}
result = document.evaluate(XPATH_STYLE, element, null, XPathResult.ANY_TYPE, null);
while ((attr = result.iterateNext())) {
if (!isStyleSecure(attr.nodeValue)) {
return false;
}
}
return true;
}
};
而且最初的想法是創建DocumentFragment的,並然後使用treeWalker檢查它的節點,或者使用.firstChild等跟隨dom樹。但是我想這個解決方案是不安全的,因爲它會讓我對所有注入的腳本都打開。我對嗎?
有沒有其他辦法?
請確保你在服務器端做同樣的事情... –
編寫你自己的HTML淨化器的問題大多數時候人們試圖擦除有效的HTML,但瀏覽器設置爲處理無效的SGML,所以存在很多漏洞,用戶可能上傳的東西看起來像無效的HTML,但實際上起作用,而淨化器從未抓到。最好採用已經在社區中的一個,如果您覺得自己找到了漏洞,請提交更新 - 幫助所有人解決問題。 – vol7ron