cf2ee082b1
Merge branch 'main' of https://github.com/splunk/AIHoneypot
2024-11-07 13:42:02 -05:00
ff848b44ac
Create LICENSE
...
Added MIT license
2024-11-07 13:37:02 -05:00
e643ac344d
Updated TODO
2024-08-26 14:36:32 -04:00
a73fefa9c4
Moved SSH honeypot to subdirectory
2024-08-26 14:31:52 -04:00
2461b42e40
Improved end-of-session handling
...
Rather than explicitly checking to see if the user
was typing a shell exit command, the LLM is now
instructed to provide a specific token starting
("XXX-END-OF-SESSION-XXX") to indicate that the
session should be closed. This allows the user to
exit the shell in any way they see fit, and the
LLM will still know when to end the session. It
also means that typing 'exit' or similar commands
to subshells or command interpreters (e.g. Python)
are less likely to cause the session to end.
2024-08-23 15:28:42 -04:00
ed95eda824
Improved honeypot logging
...
Logs now include the protocol (SSH) and the src/dest IPs and ports on each log line.
2024-08-23 13:52:36 -04:00
e2854e960c
Now log passwords for any login attempt (failures and successes).
2024-08-23 12:41:51 -04:00
4029df5cdd
Removed a redundant import
2024-08-23 11:48:08 -04:00
b49e743e7c
Cleaned up and organized imports
2024-08-23 11:43:15 -04:00
a180bb58a2
Minor code formatting changes
2024-08-23 11:18:14 -04:00
e385b8a4bb
Removed extraneous debug prints
2024-08-22 15:39:49 -04:00
7e38c43dee
Experimental support for changing LLM providers and models in the config file.
2024-08-22 14:39:47 -04:00
df203a7a55
Log both successful and failed login attempts
2024-08-20 14:44:30 -04:00
c57cb0a240
Cleaned up sample prompt files.
2024-08-20 11:52:37 -04:00
8bb4cb3393
New file: TODO.txt
2024-08-20 09:43:54 -04:00
656872ab2c
Initial SSH emulation prompt.
2024-08-20 09:17:19 -04:00
b72acb81be
Changed name to HADES
2024-08-20 09:15:08 -04:00
ba5713d94c
Now uses config.ini for all configuration parameters.
2024-08-16 17:11:41 -04:00
f84d0b2d37
Converted start_server() to more modern idiom granting better control of server parameters.
2024-08-16 15:09:07 -04:00
0f5c4d1f69
Implement chat message history trimming to avoid overflowing the LLM context window.
2024-08-16 11:34:29 -04:00
c40444a6cc
Command output now logged as base64 string to avoid multiline issues.
2024-08-16 09:13:41 -04:00
eb4a67f094
Added a couple of conveniences:
...
* Moved the system prompt to its own file
* Added 'exit/logout/quit' support to realistically end the SSH session.
2024-08-15 16:50:42 -04:00
092ac94b05
Now a function prototype with an LLM backend.
...
* Added langchain support (OpenAI's gpt-4o model)
* Created a system prompt that gives functional results
* Initial integration of logging for LLM responses (needs improvement)
2024-08-15 15:44:54 -04:00
759814f8c9
Added requirements.txt
2024-08-15 13:33:08 -04:00
62178679c6
Each SSH session now gets a uniq ID in the log
2024-08-15 13:08:45 -04:00
f95ad39f32
Added centralized logging
2024-08-15 12:17:48 -04:00
12af949915
Initial commit of barebones SSH server.
2024-08-15 11:16:37 -04:00
e7d9a8ede6
Initial commit
2024-08-15 10:55:00 -04:00
