aboutsummaryrefslogtreecommitdiffstats
path: root/dirmngr/t-http-basic.c
diff options
context:
space:
mode:
authorWerner Koch <[email protected]>2018-07-05 07:40:35 +0000
committerWerner Koch <[email protected]>2018-07-05 07:40:35 +0000
commitfaf3c70c7715ba86eb56fdccc6cf831bf87b2ee0 (patch)
tree0d86329fac47511d5170a7e0ab4fba75026a2679 /dirmngr/t-http-basic.c
parentgpg: Ignore too large user ids during import. (diff)
downloadgnupg-faf3c70c7715ba86eb56fdccc6cf831bf87b2ee0.tar.gz
gnupg-faf3c70c7715ba86eb56fdccc6cf831bf87b2ee0.zip
tools: Add experimental code for a pairing protocolseckey-sync-work
* configure.ac (GNUPG_CACHE_DIR): New const. * tools/Makefile.am (libexec_PROGRAMS): Add gpg-pair-tool. (gpg_pair_tool_SOURCES, gpg_pair_tool_CFLAGS) (gpg_pair_tool_LDADD): New. * tools/gpg-pair-tool.c: New. -- This is a first try on a protocol to pair two devices so that they can agree on a shared secret to exchange secret keys. The idea is that if you want to sync your secret keys to another machine (e.g. from desktop to mobile) you have physical access to both devices and thus a pairing protocol allows to authenitcate the connection using a short string. See the source for a protocol description. How to test: $ gpg-pair-tool -va --homedir . --initiate >msg.commit $ gpg-pair-tool -va --homedir 2ndhome --respond \ <msg.commit >msg.dhpart1 $ gpg-pair-tool -va --homedir . --respond \ <msg.dhpart1 >msg.dhpart2 $ gpg-pair-tool -va --homedir 2ndhome --respond \ <msg.dhpart2 >msg.confirm Now set the SAS as printed by the responder into SAS and run $ gpg-pair-tool -va --homedir . --respond --sas $SAS <msg.confirm Storing the secret on disk is obviously not the right thing to do. With the new PUT_SECRET and GET_SECRET commands of gpg-agent we can change this to store it all in gpg-agent instead. This will make it also easier for gpg to access the secret and we won't need an option to return it from gpg-pair-tool. Thus gpg-pair-tool can be dedicated to run the protocol and maybe to popup info dialogs. Adding a second expiration time for running the protocol in addition to the expiration of the secret is probably a better idea than just that simple catch-all TTL. Signed-off-by: Werner Koch <[email protected]>
Diffstat (limited to '')
0 files changed, 0 insertions, 0 deletions