/**
 * @name Binding a socket to all network interfaces
 * @description Binding a socket to all interfaces opens it up to traffic from any IPv4 address
 * and is therefore associated with security risks.
 * @kind problem
 * @tags security
 * @problem.severity error
 * @sub-severity low
 * @precision high
 * @id py/bind-socket-all-network-interfaces
 */

import python
import semmle.python.dataflow.new.DataFlow
import semmle.python.ApiGraphs

/** Gets a reference to a hostname that can be used to bind to all interfaces. */
private DataFlow::LocalSourceNode vulnerableHostname(DataFlow::TypeTracker t, string hostname) {
  t.start() and
  exists(StrConst allInterfacesStrConst |
    hostname in [
        // IPv4
        "0.0.0.0", "",
        // IPv6
        "::", "::0"
      ]
  |
    allInterfacesStrConst.getText() = hostname and
    result.asExpr() = allInterfacesStrConst
  )
  or
  // Due to bad performance when using normal setup with `vulnerableHostname(t2, hostname).track(t2, t)`
  // we have inlined that code and forced a join
  exists(DataFlow::TypeTracker t2 |
    exists(DataFlow::StepSummary summary |
      vulnerableHostname_first_join(t2, hostname, result, summary) and
      t = t2.append(summary)
    )
  )
}

pragma[nomagic]
private predicate vulnerableHostname_first_join(
  DataFlow::TypeTracker t2, string hostname, DataFlow::Node res, DataFlow::StepSummary summary
) {
  DataFlow::StepSummary::step(vulnerableHostname(t2, hostname), res, summary)
}

/** Gets a reference to a hostname that can be used to bind to all interfaces. */
DataFlow::Node vulnerableHostname(string hostname) {
  vulnerableHostname(DataFlow::TypeTracker::end(), hostname).flowsTo(result)
}

/** Gets a reference to tuple containing a hostname as the first element, that can be used to bind to all interfaces. */
private DataFlow::LocalSourceNode vulnerableAddressTuple(DataFlow::TypeTracker t, string hostname) {
  t.start() and
  result.asExpr() = any(Tuple tup | tup.getElt(0) = vulnerableHostname(hostname).asExpr())
  or
  // Due to bad performance when using normal setup with `vulnerableAddressTuple(t2, hostname).track(t2, t)`
  // we have inlined that code and forced a join
  exists(DataFlow::TypeTracker t2 |
    exists(DataFlow::StepSummary summary |
      vulnerableAddressTuple_first_join(t2, hostname, result, summary) and
      t = t2.append(summary)
    )
  )
}

pragma[nomagic]
private predicate vulnerableAddressTuple_first_join(
  DataFlow::TypeTracker t2, string hostname, DataFlow::Node res, DataFlow::StepSummary summary
) {
  DataFlow::StepSummary::step(vulnerableAddressTuple(t2, hostname), res, summary)
}

/** Gets a reference to tuple containing a hostname as the first element, that can be used to bind to all interfaces. */
DataFlow::Node vulnerableAddressTuple(string hostname) {
  vulnerableAddressTuple(DataFlow::TypeTracker::end(), hostname).flowsTo(result)
}

/**
 * Gets an instance of `socket.socket` using _some_ address family.
 *
 * See https://docs.python.org/3/library/socket.html
 */
API::Node socketInstance() { result = API::moduleImport("socket").getMember("socket").getReturn() }

from DataFlow::CallCfgNode bindCall, DataFlow::Node address, string hostname
where
  bindCall = socketInstance().getMember("bind").getACall() and
  address = bindCall.getArg(0) and
  address = vulnerableAddressTuple(hostname)
select bindCall.asExpr(), "'" + hostname + "' binds a socket to all interfaces."