From ccf5f1bc678638ee3a889207c3b96de040933962 Mon Sep 17 00:00:00 2001 From: Tim Graham Date: Tue, 14 Mar 2017 10:46:53 -0400 Subject: Fixed #27912, CVE-2017-7233 -- Fixed is_safe_url() with numeric URLs. This is a security fix. --- django/utils/http.py | 66 +++++++++++++++++++++++++++++++++++++++++- tests/utils_tests/test_http.py | 5 +++- 2 files changed, 69 insertions(+), 2 deletions(-) diff --git a/django/utils/http.py b/django/utils/http.py index 972760e..7a931a9 100644 --- a/django/utils/http.py +++ b/django/utils/http.py @@ -17,6 +17,18 @@ from django.utils.six.moves.urllib.parse import ( quote, quote_plus, unquote, unquote_plus, urlparse, urlencode as original_urlencode) +if six.PY2: + from urlparse import ( + ParseResult, SplitResult, _splitnetloc, _splitparams, scheme_chars, + uses_params, + ) + _coerce_args = None +else: + from urllib.parse import ( + ParseResult, SplitResult, _coerce_args, _splitnetloc, _splitparams, + scheme_chars, uses_params, + ) + ETAG_MATCH = re.compile(r'(?:W/)?"((?:\\.|[^"])*)"') MONTHS = 'jan feb mar apr may jun jul aug sep oct nov dec'.split() @@ -284,12 +296,64 @@ def is_safe_url(url, host=None): return _is_safe_url(url, host) and _is_safe_url(url.replace('\\', '/'), host) +# Copied from urllib.parse.urlparse() but uses fixed urlsplit() function. +def _urlparse(url, scheme='', allow_fragments=True): + """Parse a URL into 6 components: + :///;?# + Return a 6-tuple: (scheme, netloc, path, params, query, fragment). + Note that we don't break the components up in smaller bits + (e.g. netloc is a single string) and we don't expand % escapes.""" + if _coerce_args: + url, scheme, _coerce_result = _coerce_args(url, scheme) + splitresult = _urlsplit(url, scheme, allow_fragments) + scheme, netloc, url, query, fragment = splitresult + if scheme in uses_params and ';' in url: + url, params = _splitparams(url) + else: + params = '' + result = ParseResult(scheme, netloc, url, params, query, fragment) + return _coerce_result(result) if _coerce_args else result + + +# Copied from urllib.parse.urlsplit() with +# https://github.com/python/cpython/pull/661 applied. +def _urlsplit(url, scheme='', allow_fragments=True): + """Parse a URL into 5 components: + :///?# + Return a 5-tuple: (scheme, netloc, path, query, fragment). + Note that we don't break the components up in smaller bits + (e.g. netloc is a single string) and we don't expand % escapes.""" + if _coerce_args: + url, scheme, _coerce_result = _coerce_args(url, scheme) + allow_fragments = bool(allow_fragments) + netloc = query = fragment = '' + i = url.find(':') + if i > 0: + for c in url[:i]: + if c not in scheme_chars: + break + else: + scheme, url = url[:i].lower(), url[i + 1:] + + if url[:2] == '//': + netloc, url = _splitnetloc(url, 2) + if (('[' in netloc and ']' not in netloc) or + (']' in netloc and '[' not in netloc)): + raise ValueError("Invalid IPv6 URL") + if allow_fragments and '#' in url: + url, fragment = url.split('#', 1) + if '?' in url: + url, query = url.split('?', 1) + v = SplitResult(scheme, netloc, url, query, fragment) + return _coerce_result(v) if _coerce_args else v + + def _is_safe_url(url, host): # Chrome considers any URL with more than two slashes to be absolute, but # urlparse is not so flexible. Treat any url with three slashes as unsafe. if url.startswith('///'): return False - url_info = urlparse(url) + url_info = _urlparse(url) # Forbid URLs like http:///example.com - with a scheme, but without a hostname. # In that URL, example.com is not the hostname but, a path component. However, # Chrome will still consider example.com to be the hostname, so we must not diff --git a/tests/utils_tests/test_http.py b/tests/utils_tests/test_http.py index 769f163..fc8d902 100644 --- a/tests/utils_tests/test_http.py +++ b/tests/utils_tests/test_http.py @@ -117,6 +117,8 @@ class TestUtilsHttp(unittest.TestCase): r'http://testserver\me:pass@example.com', r'http://testserver\@example.com', r'http:\\testserver\confirm\me@example.com', + 'http:999999999', + 'ftp:9999999999', '\n'): self.assertFalse(http.is_safe_url(bad_url, host='testserver'), "%s should be blocked" % bad_url) for good_url in ('/view/?param=http://example.com', @@ -127,7 +129,8 @@ class TestUtilsHttp(unittest.TestCase): 'HTTPS://testserver/', '//testserver/', 'http://testserver/confirm?email=me@example.com', - '/url%20with%20spaces/'): + '/url%20with%20spaces/', + 'path/http:2222222222'): self.assertTrue(http.is_safe_url(good_url, host='testserver'), "%s should be allowed" % good_url) if six.PY2: