GPT_Vuln-analyzer
Uses ChatGPT API, Bard API, and Llama2, Python-Nmap, DNS Recon, PCAP and JWT recon modules and uses the GPT3 model to create vulnerability reports based on Nmap
What is GPT_Vuln-analyzer?
Uses ChatGPT API, Bard API, and Llama2, Python-Nmap, DNS Recon, PCAP and JWT recon modules and uses the GPT3 model to create vulnerability reports based on Nmap scan data, and DNS scan information. It can also perform subdomain enumeration to a great extent
Overview of GPT_Vuln-analyzer
What it is
GPT_Vuln-analyzer (GVA) is an AI-assisted reconnaissance and vulnerability-analysis toolkit. It runs scans (nmap, DNS, subdomains, JWT, PCAP, GeoIP), then hands the raw output to a large language model that returns a structured, pentester-oriented analysis. It ships with both a command-line interface and a desktop GUI. The AI layer is provider-agnostic: OpenAI, Anthropic Claude, Google Gemini, and local Ollama models are all supported. Pick one, or run several at once and let a deliberation agent reconcile their analyses into a single report.
Key features
- Nmap analysis — ten curated scan profiles, from a fast unprivileged triage to a full-port SYN audit, with the results explained by the AI.
- DNS recon — forward, reverse, and zone-transfer lookups, analysed into typed records.
- Subdomain enumeration — resolve a wordlist of subdomains against a domain.
- JWT analysis — decode a token and surface likely attacks and endpoints to test.
- PCAP analysis — inspect a capture for traffic, ARP/MAC spoofing, and cleartext credentials.
- GeoIP lookup — geolocate an IP via ipgeolocation.io.
- Password cracking — wordlist and brute-force cracking with common hash algorithms.
- Multi-provider AI — validated structured output via Pydantic AI, with concurrent analysis and a deliberation step across models.
Use cases
- Security researchers performing reconnaissance and vulnerability analysis on target systems.
- Penetration testers who want AI-generated explanations of scan results.
- Red team operations requiring automated, structured reports from multiple AI providers.
- Educational environments for learning about network scanning and vulnerability assessment.
Getting started
bash ./install.sh # full install ./install.sh --no-system # skip system packages (uv + Python deps only) For manual installation: bash uv sync Or as a fallback: bash pip install -r requirements.txt Copy the example environment file and fill in keys: bash cp .env.example .env
License and pricing
The project is licensed under MIT. It is open source and free to use. API keys for AI providers (OpenAI, Anthropic, Google Gemini) may incur costs based on their own pricing. Ollama runs locally and is free.
Based on the project's public README and repository metadata.
