š Cybersecurity-Dolphin-2.9.3-Mistral-NeMo-12B-GGUF
This is the GGUF repository of Cybersecurity-Dolphin-2.9.3-Mistral-NeMo-12B, a model specifically designed for offensive and defensive technical cybersecurity tasks.

š Quick Start
This model is tailored for offensive & defensive technical cybersecurity tasks. You can start exploring its capabilities by referring to the sample conversation below.
⨠Features
- Specialized for Cybersecurity: Ideal for red - team, blue - team, and CTI experiments.
- Quantized Model: Available in GGUF format with quantization options like q8_0 and 4bit.
š¦ Installation
No specific installation steps are provided in the original document.
š» Usage Examples
Basic Usage
The following is a sample conversation demonstrating how the model can be used in a penetration - testing scenario:
Text - Gen - WebUI chat
User:
Acting as a penetration tester - Scenario Context:
User 'Smith' has local administrator privileges on a Windows machine in the xyz.com domain.
A Domain Admin account (da03) has active login sessions/credentials cached on this machine.
Objective:
Provide a technical walkthrough explaining:
Credential Extraction: How to dump da03's NTLM hash from the compromised host (focus on Mimikatz methodology, including LSASS interaction and relevant commands).
Privilege Escalation: How to perform a Pass - the - Hash (PtH) attack using the stolen hash to gain Domain Admin privileges.
Include critical considerations (e.g., AV evasion, lateral movement potential, and domain persistence risks).
Assistant:
Absolutely, I will provide a comprehensive technical walkthrough on how to extract the da03's NTLM hash from the compromised host and perform a Pass - the - Hash (PtH) attack to gain Domain Admin privileges. I will also address critical considerations such as AV evasion, lateral movement potential, and domain persistence risks.
Credential Extraction Using Mimikatz
- Understanding Mimikatz: Mimikatz is a powerful tool for extracting credentials from Windows systems. It can dump various types of credentials, including NTLM hashes, which are used in Pass - the - Hash attacks.
- Compromise the Local Machine: Since Smith has local administrator privileges, we can execute Mimikatz on the compromised host.
- Extracting NTLM Hashes: Use the following Mimikatz command to dump the NTLM hashes:
sekurlsa::logonPasswords full
This command will dump all the credentials, including the NTLM hash of the da03 account.
- Extracting the Target Hash: From the output, locate the da03 account and note the NTLM hash.
Privilege Escalation Using Pass - the - Hash
- Understanding Pass - the - Hash: PtH is an attack where the attacker uses the NTLM hash of a legitimate user to authenticate to other systems without knowing the plaintext password.
- Using Mimikatz for PtH: Mimikatz can be used to perform a PtH attack. The command is:
sekurlsa::pth /user:da03 /domain:xyz.com /ntlm:<NTLM_Hash> /run:cmd.exe
Replace <NTLM_Hash> with the NTLM hash of da03.
- Executing the Attack: This command will create a new session with the da03 account's privileges.
Critical Considerations
⢠AV Evasion: Obfuscate or recompile Mimikatz to evade detection.
⢠Lateral Movement: Use the stolen credentials carefully; clean up logs/artifacts.
⢠Domain Persistence: Consider additional backdoors or accounts for long - term access.
⢠Credential Management & Testing: Store hashes securely and validate access sparingly.
š Documentation
Training pipeline
Phase |
Dataset(s) |
1. Continual pre - train |
Primus FineWeb - Red & FineWeb - Blue |
2. SFT |
Primus - Instruct |
3. SFT |
Primus - Reasoning |
Intended use & scope
- Research & lab tooling for red - team, blue - team and CTI experiments (e.g., exploit sketches, rule drafts, log - query ideas).
- Not for broad general - purpose deployment. The model may output uncensored content.
š License
This project is licensed under the Apache 2.0 license.
Property |
Details |
Model Type |
cybersecurity - dolphin - 2.9.3 - mistral - nemo - 12b - gguf |
Training Data |
Continual pre - train: Primus FineWeb - Red & FineWeb - Blue; SFT: Primus - Instruct, Primus - Reasoning |
Quantized From |
HagalazAI/cybersecurity - dolphin - 2.9.3 - mistral - nemo - 12b |
Tags |
gguf, q8_0, quantized, cybersecurity, red - team, blue - team, 4bit |