Can this be improved? Scrubing of dangerous html tags.

Posted by chobo2 on Stack Overflow See other posts from Stack Overflow or by chobo2
Published on 2010-06-10T22:53:12Z Indexed on 2010/06/10 23:13 UTC
Read the original article Hit count: 249

Filed under:
|
|
|

I been finding that for something that I consider pretty import there is very little information or libraries on how to deal with this problem.

I found this while searching. I really don't know all the million ways that a hacker could try to insert the dangerous tags.

I have a rich html editor so I need to keep non dangerous tags but strip out bad ones.

So is this script missing anything?

It uses html agility pack.

public string ScrubHTML(string html)
{
    HtmlDocument doc = new HtmlDocument();
    doc.LoadHtml(html);

    //Remove potentially harmful elements
    HtmlNodeCollection nc = doc.DocumentNode.SelectNodes("//script|//link|//iframe|//frameset|//frame|//applet|//object|//embed");
    if (nc != null)
    {
        foreach (HtmlNode node in nc)
        {
            node.ParentNode.RemoveChild(node, false);

        }
    }

    //remove hrefs to java/j/vbscript URLs
    nc = doc.DocumentNode.SelectNodes("//a[starts-with(translate(@href, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'javascript')]|//a[starts-with(translate(@href, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'jscript')]|//a[starts-with(translate(@href, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'vbscript')]");
    if (nc != null)
    {

        foreach (HtmlNode node in nc)
        {
            node.SetAttributeValue("href", "#");
        }
    }


    //remove img with refs to java/j/vbscript URLs
    nc = doc.DocumentNode.SelectNodes("//img[starts-with(translate(@src, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'javascript')]|//img[starts-with(translate(@src, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'jscript')]|//img[starts-with(translate(@src, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'vbscript')]");
    if (nc != null)
    {
        foreach (HtmlNode node in nc)
        {
            node.SetAttributeValue("src", "#");
        }
    }

    //remove on<Event> handlers from all tags
    nc = doc.DocumentNode.SelectNodes("//*[@onclick or @onmouseover or @onfocus or @onblur or @onmouseout or @ondoubleclick or @onload or @onunload]");
    if (nc != null)
    {
        foreach (HtmlNode node in nc)
        {
            node.Attributes.Remove("onFocus");
            node.Attributes.Remove("onBlur");
            node.Attributes.Remove("onClick");
            node.Attributes.Remove("onMouseOver");
            node.Attributes.Remove("onMouseOut");
            node.Attributes.Remove("onDoubleClick");
            node.Attributes.Remove("onLoad");
            node.Attributes.Remove("onUnload");
        }
    }

    // remove any style attributes that contain the word expression (IE evaluates this as script)
    nc = doc.DocumentNode.SelectNodes("//*[contains(translate(@style, 'ABCDEFGHIJKLMNOPQRSTUVWXYZ', 'abcdefghijklmnopqrstuvwxyz'), 'expression')]");
    if (nc != null)
    {
        foreach (HtmlNode node in nc)
        {
            node.Attributes.Remove("stYle");
        }
    }

    return doc.DocumentNode.WriteTo();
} 

© Stack Overflow or respective owner

Related posts about c#

Related posts about .NET