#5871: protect against header injection attacks.

This makes Header.encode throw a HeaderParseError if it winds up
formatting a header such that a continuation line has no leading
whitespace and looks like a header.  Since Header accepts values
containing newlines and preserves them (and this is by design), without
this fix any program that took user input (say, a subject in a web form)
and passed it to the email package as a header was vulnerable to header
injection attacks.  (As far as we know this has never been exploited.)

Thanks to Jakub Wilk for reporting this vulnerability.

1 files changed, 9 insertions, 1 deletions

diff --git a/Lib/email/header.py b/Lib/email/header.py
index f90883f..35cdb2b 100644
--- a/Lib/email/header.py
+++ b/Lib/email/header.py
@@ -47,6 +47,10 @@ ecre = re.compile(r'''
 # For use with .match()
 fcre = re.compile(r'[\041-\176]+:$')
 
+# Find a header embeded in a putative header value.  Used to check for
+# header injection attack.
+_embeded_header = re.compile(r'\n[^ \t]+:')
+
 
 
 # Helpers
@@ -320,7 +324,11 @@ class Header:
             if len(lines) > 1:
                 formatter.newline()
             formatter.add_transition()
-        return formatter._str(linesep)
+        value = formatter._str(linesep)
+        if _embeded_header.search(value):
+            raise HeaderParseError("header value appears to contain "
+                "an embedded header: {!r}".format(value))
+        return value
 
     def _normalize(self):
         # Step 1: Normalize the chunks so that all runs of identical charsets