/*
*
*  Web Application Firewall built with Cloudflare workers
*
*  Author:  < https://twitter.com/dustyfresh >
*
*  License: GPLv3 < https://www.gnu.org/licenses/gpl-3.0.en.html >
*
*  Cloudflare worker documentation:
*  < https://developers.cloudflare.com/workers/about/ >
*
*  Event logging is with Loggly
*  < https://www.loggly.com/docs/http-endpoint/ >
*
*/

/*
  Start of variable config

  - Each request starts with a risk score of 0
  - Any request with a risk score greater than safe_score will be dropped
*/

var score = 0;
var safe_score = 50;

// Set this to 1 if you are using static hosting like S3 that can't process POST requests.
// Set to 0 if your backend will handle POST requests
var no_post = 0;

// loggly HTTP/S Event Endpoint to send logs to
// https://www.loggly.com/docs/http-endpoint/
var LOGGLY_ENDPOINT = 'changeme'

// error handling
function handle_error(err){
  console.log(err);
}

// event logging
function log_violation(msg){
  console.log(msg);
}

function high_risk_event(input){
  // things that go here should always have higher weight because it's definitely
  // considered bad.
  var bad_input = [
    '%00',
    'eval(',
    'alert(',
    '<?',
    'javascript:',
    '<script>',
    '\00',
    'system(',
    'file://',
    'php://',
    'gopher://',
    'ftp://',
    'sftp://',
    'zlib://',
    'data://',
    'glob://',
    '$(',
    '`',
    'cmd.exe',
  ]
  bad_input.forEach(function(sig){
    if(input.includes(sig)){
      score += 100;
      log_violation('detected '+sig+' in the user-agent header');
    }
  });
}

// Process user-agent for malicious things
function process_user_agent(ua){
  high_risk_event(ua);
  // process user-agent with our list of regular expression signatures
  var bad_agent_regexp = [
    'python',
    'curl',
    'java',
    'wget',
    'lynx',
    'eval',
    'fake',
    'w00t',
    'perl',
    'spider', // arachnophobia was the best movie of all time
    'burp',
    'acunetix',
    'desu',
    'wpscan',
    'dirbuster',
    'sqlmap',
    'evil',
    'masscan',
    'requests',
    'shodan',
    'scan.lol',
    'nikto',
    'nmap',
    '`',
    "'{1}", // start of some sqli sigs
    'union',
    'update',
    'delete',
    'insert',
    'table',
    'from',
    'ascii',
    'hex',
    'drop',
    'eval',
  ]
  bad_agent_regexp.forEach(function(sig){
    var regexp = new RegExp(sig);
    if(regexp.test(ua)){
      score += 100;
      log_violation('detected '+sig+' in the user-agent header');
    }
  });
}

// Process URL
function process_url(url){
  high_risk_event(url);

  var bad_url_sigs = [
    '..\/{1,}etc',
    "'{1}"
  ]
  bad_url_sigs.forEach(function(sig){
    var regexp = new RegExp(sig);
    if(regexp.test(url)){
      score += 100;
      log_violation('detected '+sig+' in the url');
    }
  });
}

// Process POST input before sending to the backend
function process_post(postData){
  high_risk_event(postData);

  // start of regexp sigs
  var bad_post_sigs = [
    '..\/{1,}etc',
    "'{1}"
  ]
  bad_post_sigs.forEach(function(sig) {
    var regexp = new RegExp(sig);
    if(regexp.test(postData)){
      score += 100;
      log_violation('detected '+sig+' in POST data');
    }
  });
}

// start the CF worker event listener
addEventListener('fetch', event => {
  event.respondWith(fetchAndApply(event.request))
});

async function fetchAndApply(request) {
  // We catch the exception and set ua to 0 if there
  // is not user-agent header in the request
  try {
    // start user-agent analysis
    var ua = request.headers.get('user-agent').toLowerCase();
    process_user_agent(ua, score);
  } catch(err) {
    var ua = 0;
  }

  // start URL analysis
  var url = request.url.toLowerCase();
  process_url(decodeURIComponent(url), score);

  // inspect POST requests for bad things
  if(request.method == 'POST'){
    if(no_post == 1){
      return new Response('Method not allowed', {status: 405, statusText: 'denied'});
    } else {
      let body = await request.text()
      let formData = new URLSearchParams(body)
      process_post(decodeURIComponent(formData));

      // we log all POST data to loggly (todo: change this to be json data that is sent to loggly)
      let headers = {'Content-Type': 'content-type:text/plain' }
      const init = { method: 'POST', headers: headers, body: '{ "event": "post_request", "score": ' + score + ', "payload": "' + decodeURIComponent(body) + '", "url": "' + decodeURIComponent(request.url) + '" }' }
      const response = await fetch(LOGGLY_ENDPOINT, init);
        // check request threat score
      if(score > safe_score){
        // return 403 page if POST check does not pass the process_post function
        let headers = {'Content-Type': 'content-type:text/plain' }
        const init = { method: 'POST', headers: headers, body: '{ "event": "firewall", "score": ' + score + ', "payload": "' + decodeURIComponent(body) + '", "url": "' + decodeURIComponent(request.url) + '" }' }
        const response = await fetch(LOGGLY_ENDPOINT, init);
        return new Response('(╯°□°)╯︵ ┻━┻', {status: 403, statusText: 'Forbidden'});
      } else {
        // return request to backend with POST params since they are not bad
        let newRequest = new Request(request, { body })
        return fetch(newRequest);
      }
    }
  } else {
    // proceed with GET request scoring
    if(score > safe_score){
      let headers = {'Content-Type': 'content-type:text/plain' }
      const init = { method: 'POST', headers: headers, body: '{ "event": "firewall", "score": ' + score + ', "url": "' + decodeURIComponent(request.url) + '" }' }
      const response = await fetch(LOGGLY_ENDPOINT, init);
      return new Response('(╯°□°)╯︵ ┻━┻', {status: 403, statusText: 'Forbidden'});
    } else {
      return fetch(request);
    }
  }
}