Take Me Back to the Good Old Days

Dictionary attacks used to be the bread and butter of pentesting – simple, effective, and as reliable as a swiss army knife. But here's the catch: companies got wise, and passwords got complex. The once trusty wordlists are starting to resemble VHS tapes in the Netflix world. Nostalgic? Perhaps. Outdated? Definitely.

Who's still hanging onto 'password123' when your dog's Instagram account demands an uppercase letter, symbol, and the plot twist from a Christopher Nolan movie?

Customizing wordlists is the next logical step, but it's a time sink, and time is a premium commodity when you’re poring over lines of code trying to find a backdoor. Manually tailoring a wordlist for each new client sounds good in theory, like hand-crafting your own artisanal coffee blend every morning, but what team has the time for that?

And online generators? Static. Uninspired. They give you a handful of parameters to play with, but even then, the end product is like picking a paint-by-numbers kit versus a blank canvas. You’re in control of the colors, but the scene’s already sketched out, the template is inflexible. It lacks the personal touch that is needed to match the unique security posture of a well-guarded enterprise network.

A Scalpel, Not a Sledgehammer

I created a Python script that leverages GPT-4 to generate wordlists customized for specific targets. Some pentesters use the term “customized dictionary creation.”

Step 1: Input Target Info

The script kicks off with a straightforward Q&A session. Here you'll input target information: the company name, any abbreviations, industry type, product names, employee names, and other unique tidbits like local lingo or birthdays. Essentially, anything that GPT-4 can use as ammunition to generate potential passwords.

Step 2: Password Complexity Criteria

You'll set the bar for password complexity here by specifying minimum lengths, requirements for capital letters, numbers, and symbols. This makes sure each item on the wordlist isn’t automatically invalidated by password policy rules.

Step 3: Retrieve and Deploy

GPT-4 will work its magic, and the results will be saved in a txt file. The outputs are stored in the dictionary folder under the filename specified in the prompts.

Example Results

Texas@2023
Semiconductor$1
JohnDoe#123
TI_employee8!
TexasInst@321
DoeJohn!789
SecureTI#456
Instruments$2
John&Texas9
Passw0rd!TI
Doe#Semicon8
JohnTexas!2
TI#2023Pass
Innovate@8TI
SemiCon!1234
Electron1c$
Texas!4John
Doe8#Insts
Chip$Maker9
Circu1tTI!
Microch1p#2
Texas#Engin8
SiliconVal3y!
Dallas!Sem1
TI_Dallas4$
In$trument8
DoeSecure!3
Transist8#r
Texas&Chips
HighTech9@TI
Innov8!@TI
Semicon2019!
Texas!2021TI
JohnDoe$2022
PasswordTI$1
T3chnology!
Advanced8#TI
TiP@ssword2
Doe!Texas12
SiliconJohn!
Instruments!3
Doe8*Doe8
TI_JohnDoe4$
Chipset@88
John$Texas2
TexasDoe!23
TI@Semicon8
SecureChip9#
JobJohnTI#1
Instruments2023!

Check out the Github repo here to try it out for yourself.

Happy hunting!

Disclaimer

This tool is intended for ethical pentesting, educational, and research purposes only. The authors are not responsible for any misuse or damage caused by this tool. Always obtain proper authorization before conducting penetration testing.