Fix mishandled semicolons in the userinfo subcomponent, bsc#1226419

OBS-URL: https://build.opensuse.org/package/show/network:utilities/wget?expand=0&rev=125

properly-re-implement-userinfo-parsing.patch

@@ -0,0 +1,74 @@
+From ed0c7c7e0e8f7298352646b2fd6e06a11e242ace Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Tim=20R=C3=BChsen?= <tim.ruehsen@gmx.de>
+Date: Sun, 2 Jun 2024 12:40:16 +0200
+Subject: Properly re-implement userinfo parsing (rfc2396)
+
+* src/url.c (url_skip_credentials): Properly re-implement userinfo parsing (rfc2396)
+
+The reason why the implementation is based on RFC 2396, an outdated standard,
+is that the whole file is based on that RFC, and mixing standard here might be
+dangerous.
+---
+ src/url.c | 40 ++++++++++++++++++++++++++++++++++------
+ 1 file changed, 34 insertions(+), 6 deletions(-)
+
+diff --git a/src/url.c b/src/url.c
+index 69e948b..07c3bc8 100644
+--- a/src/url.c
++++ b/src/url.c
+@@ -41,6 +41,7 @@ as that of the covered work.  */
+ #include "url.h"
+ #include "host.h"  /* for is_valid_ipv6_address */
+ #include "c-strcase.h"
++#include "c-ctype.h"
+ 
+ #ifdef HAVE_ICONV
+ # include <iconv.h>
+@@ -526,12 +527,39 @@ scheme_leading_string (enum url_scheme scheme)
+ static const char *
+ url_skip_credentials (const char *url)
+ {
+-  /* Look for '@' that comes before terminators, such as '/', '?',
+-     '#', or ';'.  */
+-  const char *p = (const char *)strpbrk (url, "@/?#;");
+-  if (!p || *p != '@')
+-    return url;
+-  return p + 1;
++  /*
++   * This whole file implements https://www.rfc-editor.org/rfc/rfc2396 .
++   * RFC 2396 is outdated since 2005 and needs a rewrite or a thorough re-visit.
++   *
++   * The RFC says
++   * server        = [ [ userinfo "@" ] hostport ]
++   * userinfo      = *( unreserved | escaped | ";" | ":" | "&" | "=" | "+" | "$" | "," )
++   * unreserved    = alphanum | mark
++   * mark          = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
++   */
++  static const char *allowed = "-_.!~*'();:&=+$,";
++
++  for (const char *p = url; *p; p++)
++    {
++      if (c_isalnum(*p))
++        continue;
++
++      if (strchr(allowed, *p))
++        continue;
++
++      if (*p == '%' && c_isxdigit(p[1]) && c_isxdigit(p[2]))
++        {
++          p += 2;
++          continue;
++        }
++
++      if (*p == '@')
++        return p + 1;
++
++      break;
++    }
++
++  return url;
+ }
+ 
+ /* Parse credentials contained in [BEG, END).  The region is expected
+-- 
+cgit v1.1

wget.changes

@@ -1,3 +1,11 @@
+-------------------------------------------------------------------
+Tue Jun 18 07:54:22 UTC 2024 - Valentin Lefebvre <valentin.lefebvre@suse.com>
+
+- Fix mishandled semicolons in the userinfo subcomponent could lead to an
+  insecure behavior in which data that was supposed to be in the userinfo
+  subcomponent is misinterpreted to be part of the host subcomponent.
+  [bsc#1226419, properly-re-implement-userinfo-parsing.patch] 
+
 -------------------------------------------------------------------
 Sun Mar 10 20:45:15 UTC 2024 - Andreas Stieger <andreas.stieger@gmx.de>
 

wget.spec

@@ -1,7 +1,7 @@
 #
 # spec file for package wget
 #
-# Copyright (c) 2023 SUSE LLC
+# Copyright (c) 2024 SUSE LLC
 # Copyright (c) 2024 Andreas Stieger <Andreas.Stieger@gmx.de>
 #
 # All modifications and additions to the file contributed by third parties
@@ -35,6 +35,7 @@ Patch7:         wget-fix-pod-syntax.diff
 Patch8:         wget-errno-clobber.patch
 Patch9:         remove-env-from-shebang.patch
 Patch10:        wget-do-not-propagate-credentials.patch
+Patch11:        properly-re-implement-userinfo-parsing.patch
 BuildRequires:  gpgme-devel >= 0.4.2
 BuildRequires:  libcares-devel
 BuildRequires:  libidn2-devel