Reject invalid 5-byte sequences when detecting UTF-8 encoding

* src/coding.c (detect_coding_utf_8): Reject multibyte sequences
whose leading byte is greater than MAX_MULTIBYTE_LEADING_CODE.
(Bug#31829)
* src/character.h (MAX_MULTIBYTE_LEADING_CODE): Add commentary
about the connection between the value of this macro and MAX_CHAR.

1 files changed, 4 insertions, 1 deletions

diff --git a/src/coding.c b/src/coding.c
index e756ba169dd..b1eb2edb497 100644
--- a/src/coding.c
+++ b/src/coding.c
@@ -1225,7 +1225,10 @@ detect_coding_utf_8 (struct coding_system *coding,
       ONE_MORE_BYTE (c4);
       if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4))
         break;
-      if (UTF_8_5_OCTET_LEADING_P (c))
+      if (UTF_8_5_OCTET_LEADING_P (c)
+          /* If we ever need to increase MAX_CHAR, the below may need
+             to be reviewed.  */
+          && c < MAX_MULTIBYTE_LEADING_CODE)
         {
           nchars++;
           continue;