priknowsit/VertexShield
GitHub: priknowsit/VertexShield
Stars: 0 | Forks: 0
# VertexShield
VertexShield is an **Agentic Security Assessment & Threat Intelligence Platform** built on Google Cloud Platform, Vertex AI, and modern React. It automates perimeter reconnaissance, correlates threat intelligence vectors, maps CVSS-aligned risk liabilities, and produces executive/engineering briefs using a secure, custom-coordinated multi-agent chain.
## 🏗️ Architectural Topology
┌────────────────────────────────────────────────────────┐
│ VERTEXSHIELD FRONTEND │
│ (React + Vite + TailwindCSS) │
└──────────────────────────┬─────────────────────────────┘
│ [HTTPS REST Polling]
▼
┌────────────────────────────────────────────────────────┐
│ VERTEXSHIELD EXPRESS API │
│ (NodeJS Server) │
└──────────────────────────┬─────────────────────────────┘
│
┌──────────────────┬───────────────────┼──────────────────┬─────────────────┐
│ (Node 1) │ (Node 2) │ (Node 3) │ (Node 4) │ (Node 5)
▼ ▼ ▼ ▼ ▼
┌───────────┐ ┌───────────┐ ┌───────────┐ ┌───────────┐ ┌───────────┐
│ RECON │ ───> │ INTEL │ ── > │ RISK │ ───> │ RESEARCH │ ──> │ REPORTING │
│ AGENCY │ │ ANALYST │ │ CALCULATOR│ │ DEEP-DIVE│ │ COMPILERS │
└───────────┘ └───────────┘ └───────────┘ └───────────┘ └───────────┘
│ │ │ │ │
└──────────────────┴─────────┬─────────┴──────────────────┴─────────────────┘
│ [Server-Side Chain JSON payload Proxy]
▼
┌────────────────────────────────────────────────────────┐
│ GOOGLE VERTEX AI │
│ (Gemini 3.5 Flash Model Core) │
└────────────────────────────────────────────────────────┘
## 🤖 Orchestrated Multi-Agent Logic
VertexShield operates as a self-correcting sequential graph utilizing 5 distinct defensive agent nodes:
1. **Recon Agent (Passive Inspector)**:
- *Behavior*: Maps active technologies, domain WHOIS tags, open HTTP header disclosures, and SSL signatures.
- *Safety*: Remains strictly passive. Never launches active penetrations or stateful exploits.
2. **Intelligence Agent (Source Correlator)**:
- *Behavior*: Aggregates global threat databases (CVE/CWE repositories) to map matching vulnerability attributes.
3. **Risk Analysis Agent (CVSS Estimator)**:
- *Behavior*: Quantifies operational liabilities into standard CVSS likelihood and impact ratios (0-100 score).
4. **Research Agent (Academic Deep-Dive)**:
- *Behavior*: Examines software dependencies configuration offsets and tracks historical system exposes.
5. **Report Agent (Remediation Compiler)**:
- *Behavior*: Synthesizes detailed findings into actionable executive summaries and step-by-step mitigation plans.
6. **Reviewer Agent (Fact-Checking Auditor)**:
- *Behavior*: Audits compiled metrics against logical standards, calculating a pipeline confidence score (0-100%) and wiping potential hallucinations.
## 💼 Developer Specifications
### API Matrix
* `GET /api/stats` - Returns consolidated telemetry charts, total scanned counts, and alert distribution.
* `GET /api/assessments` - Lists historical assessment assets.
* `GET /api/assessments/:id` - Fetch detailed reports and real-time streaming logs.
* `POST /api/assessments` - Launches background multi-agent scans (`{ "target": "domain.com" }`).
* `DELETE /api/assessments/:id` - Cleans database registers.
* `GET /api/assessments/:id/export/:format` - Downloads compliance data as `csv`, `json`, or raw executive text (`txt`).
## 🚀 Cloud Native Infrastructure (Terraform GCP snippet)
# cloud/main.tf - Provisioning Cloud Run for VertexShield
provider "google" {
project = var.gcp_project_id
region = var.gcp_region
}
resource "google_secret_manager_secret" "gemini_key" {
secret_id = "gemini-api-key"
replication {
automatic = true
}
}
resource "google_cloud_run_service" "vertexshield" {
name = "vertexshield-platform"
location = var.gcp_region
template {
spec {
containers {
image = "gcr.io/${var.gcp_project_id}/vertexshield:latest"
resources {
limits = {
memory = "1Gi"
cpu = "1000m"
}
}
env {
name = "NODE_ENV"
value = "production"
}
env {
name = "GEMINI_API_KEY"
value_from {
secret_key_ref {
name = google_secret_manager_secret.gemini_key.secret_id
key = "latest"
}
}
}
}
}
}
traffic {
percent = 100
latest_revision = true
}
}
标签：自动化攻击