license: apache-2.0
datasets:

• cve
• exploitdb
• mitre
• nvd
• pentesting-scenarios
• command-logic
• redteam-steering
  language:
• en
  tags:
• cybersecurity
• pentesting
• vulnerability
• CVE
• exploit
  pretty_name: Pentest Agent Dataset - ChatML

Pentest Agent Dataset - ChatML

This dataset is part of the Pentest Agent project and contains cybersecurity data formatted for fine-tuning language models.

Data Sources

• Based on real CVEs from MITRE/NVD
• Enriched with CVSS impact metrics
• Linked to exploit code when available
• Includes real-world pentesting scenarios
• Contains command logic and execution steps
• Includes red team techniques with MITRE references
• Generated in ChatML format

Structure

Each sample contains:

• Instruction: A prompt requesting information about a CVE or pentesting task
• Output: A detailed explanation including impact data, exploit (if found), and reference links.

CVE Example

{
    "messages": [
        {
            "role": "user",
            "content": "Can you explain what CVE-2023-1234 is?"
        },
        {
            "role": "assistant",
            "content": "CVE-2023-1234 is a critical vulnerability in Example Software that allows remote code execution..."
        }
    ]
}

Pentesting Scenario Example

{
    "messages": [
        {
            "role": "user",
            "content": "Perform a penetration test with the following goal: Gain access to the internal network"
        },
        {
            "role": "assistant",
            "content": "Initial Context: The target is a corporate network with a public-facing web server...\n\nThinking Process: First, we need to identify potential entry points...\n\nReconnaissance: Begin with port scanning and service enumeration..."
        }
    ]
}

Command Logic Example

{
    "messages": [
        {
            "role": "user",
            "content": "How can I perform a network scan to identify open ports?"
        },
        {
            "role": "assistant",
            "content": "1. Use nmap to scan the target network:\n   nmap -sV 192.168.1.0/24\n2. For a more detailed scan:\n   nmap -p- -sV -sC 192.168.1.0/24"
        }
    ]
}

Red Team Example

{
    "messages": [
        {
            "role": "user",
            "content": "How can we use SNMP enumeration to find sensitive information?"
        },
        {
            "role": "assistant",
            "content": "SNMP enumeration can be used to find sensitive information by querying the Management Information Base (MIB). Use tools like snmpwalk to query the SNMP service and extract information such as device serial numbers, running services, and network configurations.\n\nMITRE References:\nMITRE ID: T1046\nMITRE Name: Network Service Scanning\nMITRE Tactics: Discovery"
        }
    ]
}

Sources

Vulnerability Data

• https://cve.mitre.org/ - CVE database
• https://nvd.nist.gov/ - National Vulnerability Database
• https://github.com/7h3r3v3n4n7/exploitdb-data - ExploitDB data repository

Pentesting & Red Team Data

• https://huggingface.co/datasets/resk-fr/pentesting-for-agents - Pentesting scenarios
• https://huggingface.co/datasets/boapro/PentestingCommandLogic - Command execution logic
• https://huggingface.co/datasets/cowWhySo/pentest-redteam-steering - Red team techniques with MITRE references

Generated by the Pentest Agent Dataset Pipeline.