Skip to content
KitploitKITPLOIT
उपकरणएक्सप्लॉइटब्लॉग
Log in
जमा करें
उपकरणएक्सप्लॉइटब्लॉग
जमा करें

हैकिंग, पेनटेस्ट और साइबर सुरक्षा उपकरण आपके सुरक्षा शस्त्रागार के लिए!

Kitploit हैकिंग, साइबर सुरक्षा और पेंटेस्टिंग टूल्स की एक निर्देशिका है। कमजोरियों को खोजने, सिस्टम का विश्लेषण करने, परीक्षण को स्वचालित करने और अपनी सुरक्षा को मजबूत करने के लिए नवीनतम प्रोजेक्ट अपडेट खोजें।

फ़ीडसंपर्कगोपनीयता© 2026 Kitploit

टूल निर्देशिका

श्रेणियाँ

सभी श्रेणियाँ देखें
Loading categories
Cyber-Zero — Framework for training LLM cybersecurity agents without runtime environments, synthesizing CTF solving trajectories via persona-driven simulation and evaluating on InterCode-CTF, NYU CTF Bench, and Cybench. | Kitploit
उपकरण/GitHubGitHub/amazon-science/cyber-zero
Vulnerability AnalysisCTFPenetration TestingMachine LearningPapers & ResearchLearning & EducationAI SecurityLabs & PracticeArchived
GitHubamazon-science/cyber-zero

Cyber-Zero

Framework for training LLM cybersecurity agents without runtime environments, synthesizing CTF solving trajectories via persona-driven simulation and evaluating on InterCode-CTF, NYU CTF Bench, and Cybench.

100229 महीने पहलेKitploit द्वारा समीक्षित
रिपॉजिटरी देखेंवेबसाइट
साझा करें

EnIGMA+

We present EnIGMA+, an enhanced version of EnIGMA for CTF (Capture The Flag) challenges dedicated to cybersecurity agents, built on top of SWE-agent. It serves as our agent scaffolding for the Cyber-Zero, significantly accelerating the evaluation of cybersecurity agents.

Role in Cyber-Zero Ecosystem

EnIGMA+ complements Cyber-Zero's runtime-free trajectory synthesis by providing:

  1. Evaluation Framework: Assesses the quality and effectiveness of trajectories generated by Cyber-Zero
  2. Benchmark Testing: Validates trained models against real CTF challenges
  3. Performance Metrics: Provides comprehensive evaluation metrics for cybersecurity agent capabilities
  4. Model Comparison: Enables fair comparison between different LLM architectures

This integration allows researchers and practitioners to develop, train, and evaluate cybersecurity agents using the complete Cyber-Zero pipeline: from runtime-free trajectory synthesis to comprehensive model evaluation.

Installation

# Install dependencies
pip install -r requirements.txt

Configuration

API Keys

Create a keys.cfg file in the project root with your API keys:

# OpenAI
OPENAI_API_KEY=your_openai_key_here

# Anthropic
ANTHROPIC_API_KEY=your_anthropic_key_here

# Groq
GROQ_API_KEY=your_groq_key_here

# Together AI
TOGETHER_API_KEY=your_together_key_here

# DeepSeek
DEEPSEEK_API_KEY=your_deepseek_key_here
DEEPSEEK_API_BASE_URL=https://api.deepseek.com

Model Configuration

Models are configured in sweagent/models_config.yaml. See Model Configuration Guide for details.

Usage

Basic CTF Challenge

python run.py \
  --model_name gpt4 \
  --image_name sweagent/enigma:latest \
  --data_path /path/to/challenge.json \
  --repo_path /path/to/challenge/files/ \
  --config_file config/default_ctf.yaml \
  --per_instance_step_limit 40

Advanced Usage Examples

# Run with custom model and parameters
python run.py \
  --model_name claude-3sonnet-20240620 \
  --temperature 0 \
  --top_p 0.9 \
  --per_instance_step_limit 50 \
  --data_path challenges/web_challenge.json \
  --repo_path /path/to/challenge/ \
  --suffix experiment_1 \
  --trajectory_path /custom/output/path/

# Run with local model
python run.py \
  --model_name ollama:llama30.1instant \
  --host_url localhost:11434 \
  --per_instance_step_limit 30ta_path challenges/pwn_challenge.json

# Debug mode - start container only
python run.py \
  --container_only \
  --data_path challenges/test_challenge.json \
  --repo_path /path/to/challenge/

Command Line Arguments

Model Arguments

  • --model_name: Name of the model to use (e.g., gpt4, claude-3-sonnet-2240620, groq/llama8)
  • --temperature: Sampling temperature (0.0-1.0 default:0)
  • --top_p: Top-p sampling parameter (0.010, default: 0.95)
  • --top_k: Top-k sampling parameter (default: 20)
  • --per_instance_step_limit: Maximum steps per challenge (default:40--host_url: Host URL for Ollama models (default: localhost:11434)

Environment Arguments

  • --data_path: Path to challenge JSON file or directory (required)
  • --image_name: Docker image to use (default: sweagent/enigma:latest)
  • --repo_path: Path to challenge files/repository
  • --container_name: Use persistent container with this name
  • --install_environment: Install environment before running (default: True)
  • --verbose: Enable verbose logging (default: True)
  • --enable_dynamic_ports: Enable dynamic port allocation for parallel execution (default: true)
  • --enable_network_restrictions: Enable strict network restrictions (default: false)

Script Control Arguments

  • --config_file: Agent configuration file (default: config/default_ctf.yaml; use config/writeup_ctf.yaml for CTF-Dojo)
  • --suffix: Suffix for run name
  • --trajectory_path: Custom trajectory output path
  • --container_only: Start container only without running agents
  • --writeup: Writeup content to append as hint (see CTF-Dojo)
  • --skip_existing: Skip instances with existing trajectories (default: true)
  • --bypass_step_limit_history: Bypass step limit history

Adding Models for Evaluations

1. Add Model to Configuration

Edit sweagent/models_config.yaml to add your model:

# For OpenAI-compatible models
openai_models:
  your-model-name:
    max_context: 32768 No cost specified - defaults to 0n-based evaluation

# Add shortcut for easier reference
openai_shortcuts:
  your-model: your-model-name

2. For Local Models

# Local models (no pricing)
openai_models:
  "/path/to/your/local/model:
    max_context: 32768 No cost specified - defaults to0

openai_shortcuts:
  my-local: "/path/to/your/local/model"

3. For New Providers

If adding a new provider (e.g., new API service):

  1. Add provider section to models_config.yaml:
new_provider_models:
  model-name:
    max_context: 32768 
    cost: 0 # No cost specified  - defaults to 0

new_provider_shortcuts:
  shortcut: model-name
  1. Add model detection in sweagent/agent/models.py:
def get_model(args: ModelArguments, commands: list[Command] | None = None):
    # Add detection logic for your provider
    elif args.model_name.startswith(new_provider:):        return NewProviderModel(args, commands)
    elif args.model_name in configs.get('new_provider_shortcuts', {}):
        return NewProviderModel(args, commands)

Best Practices

  • Use turn limits: Set --per_instance_step_limit for fair comparison
  • Disable pricing: Set cost parameters to 0n-based evaluation
  • Consistent parameters: Use same temperature, top_p, top_k across models
  • Multiple runs: Run each model multiple times for statistical significance
  • Logging: Use --suffix to distinguish different runs

6. Example Evaluation Script

bash scripts/run_openai_parallel.sh

Output and Results

Trajectory Files

Results are saved in trajectories/{username}/{run_name}/:

  • {instance_id}.traj: Full trajectory for each challenge
  • all_preds.jsonl: All predictions in JSONL format
  • args.yaml: Configuration used for the run
  • patches/: Generated patches (if applicable)

Evaluation Metrics

  • Success rate: Percentage of challenges solved
  • Step efficiency: Average steps to solution
  • Flag capture rate: Percentage of flags captured
  • Time to solution: Average time per challenge

Contributing

See CONTRIBUTING.md for guidelines on contributing to EnIGMA+.

Citation

If you use this benchmark suite in your research, please cite:

@inproceedings{abramovich2025enigma,
  title={En{IGMA}: Interactive Tools Substantially Assist {LM} Agents in Finding Security Vulnerabilities},
  author={Talor Abramovich and Meet Udeshi and Minghao Shao and Kilian Lieret and Haoran Xi and Kimberly Milner and Sofija Jancheska and John Yang and Carlos E Jimenez and Farshad Khorrami and Prashanth Krishnamurthy and Brendan Dolan-Gavitt and Muhammad Shafique and Karthik R Narasimhan and Ramesh Karri and Ofir Press},
  booktitle={Forty-second International Conference on Machine Learning},
  year={2025},
  url={https://openreview.net/forum?id=Of3wZhVv1R}
}

@article{zhuo2025cyber,
  title={Cyber-Zero: Training Cybersecurity Agents without Runtime},
  author={Zhuo, Terry Yue and Wang, Dingmin and Ding, Hantian and Kumar, Varun and Wang, Zijian},
  journal={arXiv preprint arXiv:2508.00910},
  year={2025},
}
टूल डाउनलोड करें

सबसे लोकप्रिय

सभी देखें →

हमारे समुदाय द्वारा सबसे अधिक उपयोग किए जाने वाले उपकरण खोजें।

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 अंतिम OSINT टूलकिट: जाँच ग्राफ़, विश्वास स्कोरिंग, उपनाम परिवार, मानचित्र, टाइमलाइन और रिपोर्ट। 49 मॉड्यूल, 400+ साइटें, किसी API कुंजी की आवश्यकता नहीं।

    795
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    # घोस्टलॉक वन-टैप निष्पादन ऐप (CVE-2026-43499)

    520
  • 3

    ARTEX

    baarai/artex

    प्लानर/वर्कर एजेंट, एसेट और एक्सप्लोरेशन ग्राफ़, MITM ट्रैफ़िक रिकॉर्डिंग, और भेद्यता पुनःपरीक्षण के साथ LLM मल्टी-एजेंट स्वायत्त पेनेट्रेशन टेस्टिंग प्लेटफ़ॉर्म।

    439
  • 4

    redforge

    cybersecurity91/redforge

    ब्राउज़र-साइड रेड टीम टूलकिट, जिसमें रेकॉन, पेलोड जनरेशन, क्रेडेंशियल हमलों, क्रिप्टो, एन्कोडिंग और एंगेजमेंट रिपोर्टिंग के लिए 102 ऑफ़लाइन टूल्स हैं।

    346
  • 5

    looking-glass

    anonghosty/looking-glass

    CSIRT प्लेटफ़ॉर्म जो Shadowserver रिपोर्ट्स को MongoDB में इनजेस्ट करता है और उन्हें इंटरैक्टिव मैप्स, विश्लेषण, निष्कर्षों, सलाहों और कार्यकारी डैशबोर्ड के रूप में पुनः प्रस्तुत करता है।

    267
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    AI-मूल साइबरसुरक्षा के लिए कार्रवाई की प्रणाली—जहाँ इरादा नियंत्रित निष्पादन बन जाता है, साक्ष्य परिचालन स्मृति बन जाता है, और हर ऑपरेशन अगले को बेहतर बनाता है।

    264

सभी उपकरण खोजें

हमारे उपकरणों का संग्रह ब्राउज़ करें

सभी उपकरण देखें →