DEV Community

Cover image for Bypassing Server-Side Request Forgery filters by abusing a bug in Ruby’s native resolver.
EdOverflow 🐸
EdOverflow 🐸

Posted on • Originally published at edoverflow.com on

Bypassing Server-Side Request Forgery filters by abusing a bug in Ruby’s native resolver.

Summary

This is a security advisory for a bug that I discovered in Resolv::getaddresses that enabled me to bypass multiple Server-Side Request Forgery filters. Applications such as GitLab and HackerOne were affected by this bug. The disclosure of all reports referenced in this advisory follow HackerOne’s Vulnerability Disclosure Guidelines.

This bug was assigned CVE-2017-0904.

Vulnerability Details

Resolv::getaddresses is OS-dependent, therefore by playing around with different IP formats one can return blank values. This bug can be abused to bypass exclusion lists often used to protect against SSRF.

💻 Machine 1 💻 Machine 2
ruby 2.3.3p222 (2016-11-21) [x86_64-linux-gnu] ruby 2.3.1p112 (2016-04-26) [x86_64-linux-gnu]

💻 Machine 1

irb(main):002:0> Resolv.getaddresses("127.0.0.1")
=> ["127.0.0.1"]
irb(main):003:0> Resolv.getaddresses("localhost")
=> ["127.0.0.1"]
irb(main):004:0> Resolv.getaddresses("127.000.000.1")
=> ["127.0.0.1"]
Enter fullscreen mode Exit fullscreen mode

💻 Machine 2

irb(main):008:0> Resolv.getaddresses("127.0.0.1")
=> ["127.0.0.1"]
irb(main):009:0> Resolv.getaddresses("localhost")
=> ["127.0.0.1"]
irb(main):010:0> Resolv.getaddresses("127.000.000.1")
=> [] # 😱
Enter fullscreen mode Exit fullscreen mode

This issue is reproducible in the latest stable build of Ruby:

$ ruby -v
ruby 2.4.3p201 (2017-10-11 revision 60168) [x86_64-linux]
$ irb
irb(main):001:0> require 'resolv'
=> true
irb(main):002:0> Resolv.getaddresses("127.000.001")
=> []
Enter fullscreen mode Exit fullscreen mode

Proof of concept

irb(main):001:0> require 'resolv'
=> true
irb(main):002:0> uri = "0x7f.1"
=> "0x7f.1"
irb(main):003:0> server_ips = Resolv.getaddresses(uri)
=> [] # The bug!
irb(main):004:0> blocked_ips = ["127.0.0.1", "::1", "0.0.0.0"]
=> ["127.0.0.1", "::1", "0.0.0.0"]
irb(main):005:0> (blocked_ips & server_ips).any?
=> false # Bypass
Enter fullscreen mode Exit fullscreen mode

Root cause

The following section describes the root cause of this bug. I have added some comments in the code snippets to help the reader follow along.

When we run irb in debug mode (irb -d) the following error is returned:

irb(main):002:0> Resolv.getaddresses "127.1"
Exception `Resolv::DNS::Config::NXDomain' at /usr/lib/ruby/2.3.0/resolv.rb:549 - 127.1
Exception `Resolv::DNS::Config::NXDomain' at /usr/lib/ruby/2.3.0/resolv.rb:549 - 127.1
=> []
Enter fullscreen mode Exit fullscreen mode

So the exception stems from fetch_resource() [1]. The “NXDOMAIN” response indicates that the resolver cannot find a corresponding PTR record. No surprise there, since, as we will see later on, resolv.rb uses the operating system’s resolver.

# Reverse DNS lookup on 💻 Machine 1.
$ nslookup 127.0.0.1
Server: 127.0.0.53
Address: 127.0.0.53#53

Non-authoritative answer:
1.0.0.127.in-addr.arpa name = localhost.

Authoritative answers can be found from:

$ nslookup 127.000.000.1
Server: 127.0.0.53
Address: 127.0.0.53#53

Non-authoritative answer:
Name: 127.000.000.1
Address: 127.0.0.1

# NXDOMAIN for 127.1.
$ nslookup 127.1
Server: 127.0.0.53
Address: 127.0.0.53#53

** server can't find 127.1: NXDOMAIN
Enter fullscreen mode Exit fullscreen mode

Now the following code snippets demonstrate why Resolv::getaddresses is OS-dependent.

getaddresses takes the address (name) and passes it on to each_address where once it has been resolved it is appended to the ret array.

# File lib/resolv.rb, line 100
def getaddresses(name)
  # This is the "ret" array.
  ret = []
  # This is where "address" is appended to the "ret" array.
  each_address(name) {|address| ret << address}
  return ret
end
Enter fullscreen mode Exit fullscreen mode

each_address runs the name through @resolvers.

# File lib/resolv.rb, line 109
def each_address(name)
    if AddressRegex =~ name
      yield name
      return
    end
    yielded = false
    # "name" is passed on to the resolver here.
    @resolvers.each {|r|
      r.each_address(name) {|address|
        yield address.to_s
        yielded = true
      }
      return if yielded
    }
end
Enter fullscreen mode Exit fullscreen mode

@resolvers is initialised in initialize().

# File lib/resolv.rb, line 109
def initialize(resolvers=[Hosts.new, DNS.new])
    @resolvers = resolvers
end
Enter fullscreen mode Exit fullscreen mode

Further on, initialize is actually initialised by setting config_info to nil which uses the default configuration in this case /etc/resolv.conf.

# File lib/resolv.rb, line 308
# Set to /etc/resolv.conf ¯\_(ツ)_/¯
def initialize(config_info=nil)
  @mutex = Thread::Mutex.new
  @config = Config.new(config_info)
  @initialized = nil
end
Enter fullscreen mode Exit fullscreen mode

Here is the default configuration:

# File lib/resolv.rb, line 959
def Config.default_config_hash(filename="/etc/resolv.conf")
  if File.exist? filename
    config_hash = Config.parse_resolv_conf(filename)
  else
    if /mswin|cygwin|mingw|bccwin/ =~ RUBY_PLATFORM
      require 'win32/resolv'
      search, nameserver = Win32::Resolv.get_resolv_info
      config_hash = {}
      config_hash[:nameserver] = nameserver if nameserver
      config_hash[:search] = [search].flatten if search
    end
  end
  config_hash || {}
end
Enter fullscreen mode Exit fullscreen mode

This demonstrates that Resolv::getaddresses is OS-dependent and that getaddresses returns an empty ret array when supplied with an IP address that fails during a reverse DNS lookup.

Mitigation

I suggest staying away from Resolv::getaddresses altogether and using the Socket library.

irb(main):002:0> Resolv.getaddresses("127.1")
=> []
irb(main):003:0> Socket.getaddrinfo("127.1", nil).sample[3]
=> "127.0.0.1"
Enter fullscreen mode Exit fullscreen mode

The Ruby Core dev team suggested using the same library.

The right way to check an address is using OS's resolver instead of resolv.rb if the address is resolved by OS's resolver. For example, Addrinfo.getaddrinfo of socket library can be used.

  • Tanaka Akira
% ruby -rsocket -e '
as = Addrinfo.getaddrinfo("192.168.0.1", nil)
p as
p as.map {|a| a.ipv4_private? }
'
[#<Addrinfo: 192.168.0.1 TCP>, #<Addrinfo: 192.168.0.1 UDP>, #<Addrinfo: 192.168.0.1 SOCK_RAW>]
[true, true, true]
Enter fullscreen mode Exit fullscreen mode

Affected Applications and gems

GitLab Community Edition and Enterprise Edition

Link to report: https://hackerone.com/reports/215105

The fix for Mustafa Hasan’s report (!17286) could be easily bypassed by abusing this bug. GitLab introduced an exclusion list, but would resolve the user-supplied address using Resolv::getaddresses and then compare the output to the values in the exclusion list. This meant that one could no longer use certain addresses such as http://127.0.0.1 and http://localhost/, which Mustafa Hasan used in the original report. The bypasses allowed me to scan a GitLab intance’s internal network.

Error message - Open port

Error message - Closed port

GitLab have provided a patch: https://about.gitlab.com/2017/11/08/gitlab-10-dot-1-dot-2-security-release/.

private_address_check by John Downey

Link to report: https://github.com/jtdowney/private_address_check/issues/1

private_address_check is a Ruby gem that helps prevent SSRF. The actual filtering takes place in lib/private_address_check.rb. The process starts by attempting to resolve the user-supplied URL with Resolv::getaddresses and then compares the returned value with a the values in the blacklist. Once again I was able to use the same technique as before with GitLab to bypass this filter.

# File lib/private_address_check.rb, line 32
def resolves_to_private_address?(hostname)
  ips = Resolv.getaddresses(hostname)
  ips.any? do |ip| 
    private_address?(ip)
  end
end
Enter fullscreen mode Exit fullscreen mode

Consequently, HackerOne was affected by this bypass, because they use the private_address_check gem to prevent SSRF on the “Integrations” panel: https://hackerone.com/{BBP}/integrations.

HackerOne - Blocked Address

HackerOne - Bypass

Unfortunately, I was unable to exploit this SSRF and therefore the issue only consisted of a filter bypass. HackerOne still encouraged me to report it, because they take any potential security issue into consideration and this bypass demonstrated a potential risk.

This issue was patched in version 0.4.0.

Unaffected applications and gems

ssrf_filter by Arkadiy Tetelman

This gem is not vulnerable, because it checks if the value returned is empty.

# File lib/ssrf_filter/ssrf_filter.rb, line 116
raise UnresolvedHostname, "Could not resolve hostname '#{hostname}'" if ip_addresses.empty?

irb(main):001:0> require 'ssrf_filter'
=> true
irb(main):002:0> SsrfFilter.get("http://127.1/")
SsrfFilter::UnresolvedHostname: Could not resolve hostname '127.1'
  from /var/lib/gems/2.3.0/gems/ssrf_filter-1.0.2/lib/ssrf_filter/ssrf_filter.rb:116:in `block (3 levels) in <class:SsrfFilter>'
  from /var/lib/gems/2.3.0/gems/ssrf_filter-1.0.2/lib/ssrf_filter/ssrf_filter.rb:107:in `times'
  from /var/lib/gems/2.3.0/gems/ssrf_filter-1.0.2/lib/ssrf_filter/ssrf_filter.rb:107:in `block (2 levels) in <class:SsrfFilter>'
  from (irb):2
  from /usr/bin/irb:11:in `<main>'
Enter fullscreen mode Exit fullscreen mode

faraday-restrict-ip-addresses by Ben Lavender

This gem uses Addrinfo.getaddrinfo as recommended by the Ruby Code dev team.

# File lib/faraday/restrict_ip_addresses.rb, line 61
def addresses(hostname)
      Addrinfo.getaddrinfo(hostname, nil, :UNSPEC, :STREAM).map { |a| IPAddr.new(a.ip_address) }
    rescue SocketError => e
      # In case of invalid hostname, return an empty list of addresses
      []
end
Enter fullscreen mode Exit fullscreen mode

Conclusion

The author would like to acknowledge the help provided by Tom Hudson and Yasin Soliman during the discovery of the bug.

Both John Downey and Arkadiy Tetelman were extremely responsive. John Downey was able to immediately provide a patch, and Arkadiy Tetelman helped me figure out why their gem was not affected by the issue.


Update (Friday, 10 November 2017): I expanded the “Root cause” section in order to better explain the actual issue.

Top comments (0)