[1.7.x] Made is_safe_url() reject URLs that start with control characters.

This is a security fix; disclosure to follow shortly.

1 files changed, 8 insertions, 2 deletions

diff --git a/django/utils/http.py b/django/utils/http.py
index 6aa5cd38d6..ef88f65cbe 100644
--- a/django/utils/http.py
+++ b/django/utils/http.py
@@ -5,7 +5,7 @@ import calendar
 import datetime
 import re
 import sys
-
+import unicodedata
 from binascii import Error as BinasciiError
 from email.utils import formatdate
 
@@ -270,9 +270,10 @@ def is_safe_url(url, host=None):
 
     Always returns ``False`` on an empty url.
     """
+    if url is not None:
+        url = url.strip()
     if not url:
         return False
-    url = url.strip()
     # Chrome treats \ completely as /
     url = url.replace('\\', '/')
     # Chrome considers any URL with more than two slashes to be absolute, but
@@ -286,5 +287,10 @@ def is_safe_url(url, host=None):
     # allow this syntax.
     if not url_info.netloc and url_info.scheme:
         return False
+    # Forbid URLs that start with control characters. Some browsers (like
+    # Chrome) ignore quite a few control characters at the start of a
+    # URL and might consider the URL as scheme relative.
+    if unicodedata.category(url[0])[0] == 'C':
+        return False
     return ((not url_info.netloc or url_info.netloc == host) and
             (not url_info.scheme or url_info.scheme in ['http', 'https']))