aboutsummaryrefslogtreecommitdiffstats
path: root/g10/build-packet.c
diff options
context:
space:
mode:
authorDavid Shaw <[email protected]>2003-04-30 05:33:52 +0000
committerDavid Shaw <[email protected]>2003-04-30 05:33:52 +0000
commit1fc1d26083f394a46da6a8b05b60a222cbf879f2 (patch)
treeb0acd7efa10fc3a266694bf5dfb733889e3d22e1 /g10/build-packet.c
parent* gettextP.h: Add comment for HP/UX users. Local fix for GnuPG. (diff)
downloadgnupg-1fc1d26083f394a46da6a8b05b60a222cbf879f2.tar.gz
gnupg-1fc1d26083f394a46da6a8b05b60a222cbf879f2.zip
* build-packet.c (build_sig_subpkt): Comments.
* exec.c (exec_write): Cast NULL to void* to properly terminate varargs list. * keyedit.c (show_key_with_all_names): Just for safety, catch an invalid pk algorithm. * sign.c (make_keysig_packet): Crucial that the call to mksubpkt comes LAST before the calls to finalize the sig as that makes it possible for the mksubpkt function to get a reliable pointer to the subpacket area. * pkclist.c (do_we_trust_pre): If an untrusted key was chosen by a particular user ID, use that ID as the one to ask about when prompting whether to use the key anyway. (build_pk_list): Similar change here when adding keys to the recipient list. * trustdb.c (update_validity): Fix bug that prevented more than one validity record per trust record. (get_validity): When retrieving validity for a (user) supplied user ID, return the validity for that user ID only, and do not fall back to the general key validity. (validate_one_keyblock): Some commentary on whether non-self-signed user IDs belong in the web of trust (arguably, they do).
Diffstat (limited to 'g10/build-packet.c')
-rw-r--r--g10/build-packet.c4
1 files changed, 4 insertions, 0 deletions
diff --git a/g10/build-packet.c b/g10/build-packet.c
index 92e357f7e..3fec9a84c 100644
--- a/g10/build-packet.c
+++ b/g10/build-packet.c
@@ -794,6 +794,10 @@ build_sig_subpkt (PKT_signature *sig, sigsubpkttype_t type,
case SIGSUBPKT_PRIV_VERIFY_CACHE: /*(obsolete)*/
BUG();
break;
+ /* The issuer being unhashed is a historical oddity. It
+ should work equally as well hashed. Of course, if even an
+ unhashed issuer is tampered with, it makes it awfully hard
+ to verify the sig... */
case SIGSUBPKT_ISSUER:
hashed = 0;
break;