From aab3e8c432b90508ac14755128f5a687be2fdf43 Mon Sep 17 00:00:00 2001 From: Mingli Yu Date: Thu, 22 Sep 2016 16:39:49 +0800 Subject: [PATCH] python3: fix CVE-2016-1000110 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Ignore the HTTP_PROXY variable when REQUEST_METHOD environment is set, which indicates that the script is in CGI mode. Issue #27568 Reported and patch contributed by Rémi Rampin. [#27568] Backport patch from https://hg.python.org/cpython/rev/a0ac52ed8f79 Upstream-Status: Backport CVE: CVE-2016-1000110 Signed-off-by: Mingli Yu --- Doc/howto/urllib2.rst | 5 +++++ Doc/library/urllib.request.rst | 17 ++++++++++++++++- Lib/test/test_urllib.py | 14 +++++++++++++- Lib/urllib/request.py | 6 ++++++ Misc/NEWS | 4 ++++ 5 files changed, 44 insertions(+), 2 deletions(-) diff --git a/Doc/howto/urllib2.rst b/Doc/howto/urllib2.rst index 24a4156..d2c7991 100644 --- a/Doc/howto/urllib2.rst +++ b/Doc/howto/urllib2.rst @@ -538,6 +538,11 @@ setting up a `Basic Authentication`_ handler: :: through a proxy. However, this can be enabled by extending urllib.request as shown in the recipe [#]_. +.. note:: + + ``HTTP_PROXY`` will be ignored if a variable ``REQUEST_METHOD`` is set; see + the documentation on :func:`~urllib.request.getproxies`. + Sockets and Layers ================== diff --git a/Doc/library/urllib.request.rst b/Doc/library/urllib.request.rst index 1338906..1291aeb 100644 --- a/Doc/library/urllib.request.rst +++ b/Doc/library/urllib.request.rst @@ -173,6 +173,16 @@ The :mod:`urllib.request` module defines the following functions: If both lowercase and uppercase environment variables exist (and disagree), lowercase is preferred. + .. note:: + + If the environment variable ``REQUEST_METHOD`` is set, which usually + indicates your script is running in a CGI environment, the environment + variable ``HTTP_PROXY`` (uppercase ``_PROXY``) will be ignored. This is + because that variable can be injected by a client using the "Proxy:" HTTP + header. If you need to use an HTTP proxy in a CGI environment, either use + ``ProxyHandler`` explicitly, or make sure the variable name is in + lowercase (or at least the ``_proxy`` suffix). + The following classes are provided: @@ -280,6 +290,11 @@ The following classes are provided: list of hostname suffixes, optionally with ``:port`` appended, for example ``cern.ch,ncsa.uiuc.edu,some.host:8080``. + .. note:: + + ``HTTP_PROXY`` will be ignored if a variable ``REQUEST_METHOD`` is set; + see the documentation on :func:`~urllib.request.getproxies`. + .. class:: HTTPPasswordMgr() @@ -1138,7 +1153,7 @@ the returned bytes object to string once it determines or guesses the appropriate encoding. The following W3C document, https://www.w3.org/International/O-charset\ , lists -the various ways in which a (X)HTML or a XML document could have specified its +the various ways in which an (X)HTML or an XML document could have specified its encoding information. As the python.org website uses *utf-8* encoding as specified in its meta tag, we diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py index 5d05f8d..247598a 100644 --- a/Lib/test/test_urllib.py +++ b/Lib/test/test_urllib.py @@ -1,4 +1,4 @@ -"""Regresssion tests for what was in Python 2's "urllib" module""" +"""Regression tests for what was in Python 2's "urllib" module""" import urllib.parse import urllib.request @@ -232,6 +232,18 @@ class ProxyTests(unittest.TestCase): self.assertTrue(urllib.request.proxy_bypass_environment('anotherdomain.com:8888')) self.assertTrue(urllib.request.proxy_bypass_environment('newdomain.com:1234')) + def test_proxy_cgi_ignore(self): + try: + self.env.set('HTTP_PROXY', 'http://somewhere:3128') + proxies = urllib.request.getproxies_environment() + self.assertEqual('http://somewhere:3128', proxies['http']) + self.env.set('REQUEST_METHOD', 'GET') + proxies = urllib.request.getproxies_environment() + self.assertNotIn('http', proxies) + finally: + self.env.unset('REQUEST_METHOD') + self.env.unset('HTTP_PROXY') + def test_proxy_bypass_environment_host_match(self): bypass = urllib.request.proxy_bypass_environment self.env.set('NO_PROXY', diff --git a/Lib/urllib/request.py b/Lib/urllib/request.py index 1731fe3..3be327d 100644 --- a/Lib/urllib/request.py +++ b/Lib/urllib/request.py @@ -2412,6 +2412,12 @@ def getproxies_environment(): name = name.lower() if value and name[-6:] == '_proxy': proxies[name[:-6]] = value + # CVE-2016-1000110 - If we are running as CGI script, forget HTTP_PROXY + # (non-all-lowercase) as it may be set from the web server by a "Proxy:" + # header from the client + # If "proxy" is lowercase, it will still be used thanks to the next block + if 'REQUEST_METHOD' in os.environ: + proxies.pop('http', None) for name, value in os.environ.items(): if name[-6:] == '_proxy': name = name.lower() diff --git a/Misc/NEWS b/Misc/NEWS index 4ad2551..2fcc95b 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -329,6 +329,10 @@ Library - Issue #26644: Raise ValueError rather than SystemError when a negative length is passed to SSLSocket.recv() or read(). +- Issue #27568: Prevent HTTPoxy attack (CVE-2016-1000110). Ignore the + HTTP_PROXY variable when REQUEST_METHOD environment is set, which indicates + that the script is in CGI mode. + - Issue #23804: Fix SSL recv(0) and read(0) methods to return zero bytes instead of up to 1024. -- 2.8.1