From 326d9c203b3980c0f841bc62b06e37134c6e51ea Mon Sep 17 00:00:00 2001
From: Justine Tunney <jtunney@gmail.com>
Date: Mon, 25 Jan 2021 21:34:50 -0800
Subject: Allow more scripts without #!

This change modifies the zsh binary safety check surrounding execve() so
it can run shell scripts having concatenated binary content. We're using
the same safety check as FreeBSD /bin/sh [1]. POSIX was recently revised
to require this behavior:

    "The input file may be of any type, but the initial portion of the
     file intended to be parsed according to the shell grammar (XREF to
     XSH 2.10.2 Shell Grammar Rules) shall consist of characters and
     shall not contain the NUL character. The shell shall not enforce
     any line length limits."

    "Earlier versions of this standard required that input files to the
     shell be text files except that line lengths were unlimited.
     However, that was overly restrictive in relation to the fact that
     shells can parse a script without a trailing newline, and in
     relation to a common practice of concatenating a shell script
     ending with an 'exit' or 'exec $command' with a binary data payload
     to form a single-file self-extracting archive." [2] [3]

One example use case of such scripts, is the Cosmopolitan C Library [4]
which configuse the GNU Linker to output a polyglot shell+binary format
that runs on Linux / Mac / Windows / FreeBSD / OpenBSD.

[1] https://github.com/freebsd/freebsd-src/commit/9a1cd363318b7e9e70ef6af27d1675b371c16b1a
[2] http://austingroupbugs.net/view.php?id=1250
[3] http://austingroupbugs.net/view.php?id=1226#c4394
[4] https://justine.lol/cosmopolitan/index.html
---
 Src/exec.c | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

(limited to 'Src')

diff --git a/Src/exec.c b/Src/exec.c
index ecad923de..2301f85ad 100644
--- a/Src/exec.c
+++ b/Src/exec.c
@@ -547,10 +547,29 @@ zexecve(char *pth, char **argv, char **newenvp)
 			}
 		    }
 		} else if (eno == ENOEXEC) {
-		    for (t0 = 0; t0 != ct; t0++)
-			if (!execvebuf[t0])
-			    break;
-		    if (t0 == ct) {
+                    /* Perform binary safety check on classic shell    *
+                     * scripts (shebang wasn't introduced until UNIX   *
+                     * Seventh Edition). POSIX says we shall allow     *
+                     * execution of scripts with concatenated binary   *
+                     * and suggests checking a line exists before the  *
+                     * first NUL character with a lowercase letter or  *
+                     * expansion. This is consistent with FreeBSD sh.  */
+                    int isbinary, hasletter;
+                    if (!(ptr2 = memchr(execvebuf, '\0', ct))) {
+                        isbinary = 0;
+                    } else {
+                        isbinary = 1;
+                        hasletter = 0;
+                        for (ptr = execvebuf; ptr < ptr2; ptr++) {
+                            if (islower(*ptr) || *ptr == '$' || *ptr == '`')
+                                hasletter = 1;
+                            if (hasletter && *ptr == '\n') {
+                                isbinary = 0;
+                                break;
+                            }
+                        }
+                    }
+		    if (!isbinary) {
 			argv[-1] = "sh";
 			winch_unblock();
 			execve("/bin/sh", argv - 1, newenvp);
-- 
cgit 1.4.1