From 72d356e3584ebfb8e813a8e9f2cd3dccf233c0d9 Mon Sep 17 00:00:00 2001 From: "Miss Islington (bot)" <31488909+miss-islington@users.noreply.github.com> Date: Sun, 13 Nov 2022 11:00:25 -0800 Subject: [PATCH] gh-99418: Make urllib.parse.urlparse enforce that a scheme must begin with an alphabetical ASCII character. (GH-99421) Prevent urllib.parse.urlparse from accepting schemes that don't begin with an alphabetical ASCII character. RFC 3986 defines a scheme like this: `scheme = ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )` RFC 2234 defines an ALPHA like this: `ALPHA = %x41-5A / %x61-7A` The WHATWG URL spec defines a scheme like this: `"A URL-scheme string must be one ASCII alpha, followed by zero or more of ASCII alphanumeric, U+002B (+), U+002D (-), and U+002E (.)."` (cherry picked from commit 439b9cfaf43080e91c4ad69f312f21fa098befc7) Co-authored-by: Ben Kallus <49924171+kenballus@users.noreply.github.com> --- end original header --- CVE: CVE-2023-24329 Upstream-Status: Backport [see below] Taken from https://github.com/python/cpython.git commit 72d356e3584ebfb8e813a8e9f2cd3dccf233c0d9 CVE fix extracted; test case and update to NEWS abandoned. Defuzzed. Signed-off-by: Joe Slater --- Lib/urllib/parse.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index 26ddf30..1c53acb 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -469,7 +469,7 @@ def urlsplit(url, scheme='', allow_fragments=True): clear_cache() netloc = query = fragment = '' i = url.find(':') - if i > 0: + if i > 0 and url[0].isascii() and url[0].isalpha(): for c in url[:i]: if c not in scheme_chars: break -- 2.25.1