Throwing an Exception In an Xss Attack - asp.net-core

Question

This is a Web API which Json payloads (so, no Razor).
I'm using ASP.NET Core 2.1
1st up I should mention that I am sanitizing the relevant inputs with HtmlEncoder. However, that is just in case any gets past my validator, which I want to ask about here.
I want to write a validator which will return an error code where a user tries to include an html string in an input (using a mobile app, which would be a property in the json payload).
I've seen some naive implementation suggestion here on SO - usually just checking to see of the string contains '<' or '>' (and maybe one or 2 other chars).
I guess I would like to know if that is sufficient for the task at hand. There's no reason for a user to post any kind of html/xml in this domain.
A lot of the libraries around will sanitize input. But none of them seem to have a method which tells you if a string contains potentially harmful input.
As I said, I'm already sanitizing (as a last line of defence). But ideally I would return an error code before it gets to that.

Answer 1

Use this class from Microsoft ASP.NET Core 1
// <copyright file="CrossSiteScriptingValidation.cs" company="Microsoft">
// Copyright (c) Microsoft Corporation. All rights reserved.
// </copyright>
public static class CrossSiteScriptingValidation
{
private static readonly char[] StartingChars = { '<', '&' };
#region Public methods
// Only accepts http: and https: protocols, and protocolless urls.
// Used by web parts to validate import and editor input on Url properties.
// Review: is there a way to escape colon that will still be recognized by IE?
// %3a does not work with IE.
public static bool IsDangerousUrl(string s)
{
if (string.IsNullOrEmpty(s))
{
return false;
}
// Trim the string inside this method, since a Url starting with whitespace
// is not necessarily dangerous. This saves the caller from having to pre-trim
// the argument as well.
s = s.Trim();
var len = s.Length;
if ((len > 4) &&
((s[0] == 'h') || (s[0] == 'H')) &&
((s[1] == 't') || (s[1] == 'T')) &&
((s[2] == 't') || (s[2] == 'T')) &&
((s[3] == 'p') || (s[3] == 'P')))
{
if ((s[4] == ':') || ((len > 5) && ((s[4] == 's') || (s[4] == 'S')) && (s[5] == ':')))
{
return false;
}
}
var colonPosition = s.IndexOf(':');
return colonPosition != -1;
}
public static bool IsValidJavascriptId(string id)
{
return (string.IsNullOrEmpty(id) || System.CodeDom.Compiler.CodeGenerator.IsValidLanguageIndependentIdentifier(id));
}
public static bool IsDangerousString(string s, out int matchIndex)
{
//bool inComment = false;
matchIndex = 0;
for (var i = 0; ;)
{
// Look for the start of one of our patterns
var n = s.IndexOfAny(StartingChars, i);
// If not found, the string is safe
if (n < 0) return false;
// If it's the last char, it's safe
if (n == s.Length - 1) return false;
matchIndex = n;
switch (s[n])
{
case '<':
// If the < is followed by a letter or '!', it's unsafe (looks like a tag or HTML comment)
if (IsAtoZ(s[n + 1]) || s[n + 1] == '!' || s[n + 1] == '/' || s[n + 1] == '?') return true;
break;
case '&':
// If the & is followed by a #, it's unsafe (e.g. S)
if (s[n + 1] == '#') return true;
break;
}
// Continue searching
i = n + 1;
}
}
#endregion
#region Private methods
private static bool IsAtoZ(char c)
{
return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
}
#endregion
}
Then use this middleware to control URL,Query Parameteres and Content:
public class XssMiddleware
{
private readonly RequestDelegate _next;
public XssMiddleware(RequestDelegate next)
{
if (next == null)
{
throw new ArgumentNullException(nameof(next));
}
_next = next;
}
public async Task Invoke(HttpContext context)
{
// Check XSS in URL
if (!string.IsNullOrWhiteSpace(context.Request.Path.Value))
{
var url = context.Request.Path.Value;
int matchIndex;
if (CrossSiteScriptingValidation.IsDangerousString(url, out matchIndex))
{
throw new CrossSiteScriptingException("YOUR_ERROR_MESSAGE");
}
}
// Check XSS in query string
if (!string.IsNullOrWhiteSpace(context.Request.QueryString.Value))
{
var queryString = WebUtility.UrlDecode(context.Request.QueryString.Value);
int matchIndex;
if (CrossSiteScriptingValidation.IsDangerousString(queryString, out matchIndex))
{
throw new CrossSiteScriptingException("YOUR_ERROR_MESSAGE");
}
}
// Check XSS in request content
var originalBody = context.Request.Body;
try
{
var content = await ReadRequestBody(context);
int matchIndex;
if (CrossSiteScriptingValidation.IsDangerousString(content, out matchIndex))
{
throw new CrossSiteScriptingException("YOUR_ERROR_MESSAGE");
}
await _next(context);
}
finally
{
context.Request.Body = originalBody;
}
}
private static async Task<string> ReadRequestBody(HttpContext context)
{
var buffer = new MemoryStream();
await context.Request.Body.CopyToAsync(buffer);
context.Request.Body = buffer;
buffer.Position = 0;
var encoding = Encoding.UTF8;
var contentType = context.Request.GetTypedHeaders().ContentType;
if (contentType?.Charset != null) encoding = Encoding.GetEncoding(contentType.Charset);
var requestContent = await new StreamReader(buffer, encoding).ReadToEndAsync();
context.Request.Body.Position = 0;
return requestContent;
}
}