Skip to content
KitploitKITPLOIT
ToolsExploitsBlog
Log in
Submit
ToolsExploitsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacy© 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
SBOM-VEX-Taint-Analysis — Automated SBOM-to-VEX pipeline using a secure multi-agent AI system to analyze CVEs, reason about exploitability, and generate signed CycloneDX VEX documents in compliance with OWASP GenAI guidelines. | Kitploit
Tools/GitHubGitHub/owasp/sbom-vex-taint-analysis
Vulnerability AnalysisSupply Chain SecurityPapers & ResearchLearning & EducationCurated ResourcesAI Security
GitHubowasp/sbom-vex-taint-analysis

SBOM-VEX-Taint-Analysis

Automated SBOM-to-VEX pipeline using a secure multi-agent AI system to analyze CVEs, reason about exploitability, and generate signed CycloneDX VEX documents in compliance with OWASP GenAI guidelines.

View Repository
211162 days agoNot yet reviewed
Share

SBOM → VEX Agent

Automatically generate signed CycloneDX VEX documents from SBOMs using a secure multi-agent AI pipeline built with the Microsoft Agent Framework (C# / .NET) in accordance with the OWASP GenAI Security Project guidelines.

License: MIT OWASP CycloneDX Microsoft Agent Framework

image

The Problem

Generating an SBOM surfaces hundreds of CVEs. In practice, over 90% are not exploitable in a specific product's runtime context. Without a Vulnerability Exploitability eXchange (VEX) document, every downstream tool — Dependency-Track, release gates, procurement checklists — drowns in false positives.

Read the WIKI for more technical details and results of testing.

Manual VEX generation is time-consuming and does not scale. A skilled analyst can spend hours assessing a single component. A production SBOM may contain 500–2,000 components.

This project automates that reasoning pipeline — securely, without vendor lock-in, with all data remaining on your infrastructure.

Real-world motivation: In 2024, security researcher Johanna Curiel documented exactly this problem while analysing the Kubernetes Java Client (LinkedIn article). The OSV scanner identified a high-risk CVE in com.diffplug.spotless:spotless-maven-plugin 1.17.0 in seconds. Determining it was not_affected (build-time plugin, never executed at runtime) took hours of manual analysis. This project automates that reasoning step.


Architecture

Four security zones. Nothing crosses a boundary without explicit validation.

┌─────────────────────────────────────────────────────────────────┐
│  ZONE 1 — Input ingestion (no LLM)                              │
│  SBOM upload → Schema validate → Sanitise → SHA-256 audit hash  │
└────────────────────────────┬────────────────────────────────────┘
                             │
┌────────────────────────────▼────────────────────────────────────┐
│  ZONE 2 — OWASP guardrail middleware (AIAgentBuilder.Use)       │
│  Prompt guard (LLM01) · Output filter (LLM02/05)                │
│  Agency limiter (LLM06) · Token budget & MaxMessages (LLM10)    │
└────────────────────────────┬────────────────────────────────────┘
                             │
┌────────────────────────────▼────────────────────────────────────┐
│  ZONE 3 — Multi-agent pipeline (Microsoft Agent Framework C#)   │
│                                                                  │
│  AgentWorkflowBuilder.BuildSequential                            │
│       ├── CVE Analyst       NVD v2 + OSV + EPSS per component   │
│       ├── Exploit Reasoner  Call graph · LLM reasoning · RAG    │
│       └── VEX Writer        CycloneDX 1.6 schema-validated      │
│                                                                  │
│  Vector store (Qdrant) — signed past VEX decisions              │
└────────────────────────────┬────────────────────────────────────┘
                             │
┌────────────────────────────▼────────────────────────────────────┐
│  ZONE 4 — Output, signing, audit                                │
│  Human-in-the-loop gate → cosign/GPG sign → audit log           │
└─────────────────────────────────────────────────────────────────┘

OWASP GenAI Compliance

This project is designed against the OWASP Top 10 for LLM Applications 2025 and the OWASP Top 10 for Agentic Applications 2026.

OWASP RiskIDMitigation in this project
Prompt InjectionLLM01All SBOM fields sanitised before LLM injection; injection pattern blocklist in SbomIngestor and OwaspGuardrailMiddleware
Sensitive Info DisclosureLLM02PII scrubber on all agent outputs; internal path filter (OwaspGuardrailMiddleware)
Improper Output HandlingLLM05CycloneDX 1.6 schema validation before signing; retry on failure
Excessive AgencyLLM06Read-only AIFunction tools during analysis; HITL gate for all CVSS ≥ 7.0 or affected rulings
System Prompt LeakageLLM07Internal policies separated from system prompt
Vector / Embedding WeaknessLLM08Stored vectors signed with HMAC-SHA256; provenance checked before context injection
Unbounded ConsumptionLLM10MaxMessageCount(20) in middleware; per-pipeline token budget; strict NVD/OSV HTTP timeouts

Human-in-the-loop is mandatory. A VEX not_affected or affected statement for a high-severity CVE is a legal-grade assertion. No VEX is signed without human reviewer approval. This is not configurable.


Tech Stack

ComponentToolNotes
Agent orchestrationMicrosoft Agent Framework (C# / .NET)Microsoft.Agents.AI & Microsoft.Agents.AI.Workflows (replaces legacy AutoGen)
AI abstractionsMicrosoft.Extensions.AI + Microsoft.Agents.AI.OpenAIIChatClient, AIAgent, AIFunctionFactory, AIAgentBuilder middleware
LLM (recommended)Qwen2.5-Coder-32BBest structured JSON + security reasoning
LLM servervLLM (prod) / Ollama (dev)OpenAI-compatible API (VLLM_BASE_URL)
CVE dataNVD v2 API + OSV.dev + EPSSAll free, no API key required
Vector storeQdrantSelf-hosted, provenance-signed past VEX decisions
SBOM formatsCycloneDX 1.4–1.7 (JSON), SPDX 2.2/2.3 (JSON)Schema-validated and sanitised on ingest
VEX outputCycloneDX 1.6 VEXSchema-validated before signing
Signingcosign / RSASSA-PSSTimestamped, SHA-256 payload signed, audit-logged
Audit logAppend-only JSONL / PostgreSQLEvery agent decision and signature recorded

Everything runs on-premises. No data leaves your infrastructure.


Requirements

Hardware (production):

  • 1× A100 80GB, or 2× RTX 3090 (48GB VRAM combined) for Qwen2.5-Coder-32B
  • 16GB+ system RAM
  • 100GB+ SSD for model weights and vector store

Hardware (development / small SBOMs):

  • Any machine with 16GB RAM — use llama3.1:8b via Ollama

Software:

  • .NET SDK 8.0+ / 10.0+ (dotnet)
  • Docker + Docker Compose (optional, for Qdrant / PostgreSQL)

Quick Start

1. Clone and build

git clone https://github.com/OWASP/SBOM-VEX-Taint-Analysis
cd SBOM-VEX-Taint-Analysis
dotnet build SbomVexAgent/SbomVexAgent.csproj

2. Start the LLM backend

# Development — Ollama (CPU/GPU, any laptop)
ollama pull llama3.1
ollama serve

# Production — vLLM (GPU required)
python -m vllm.entrypoints.openai.api_server \
  --model Qwen/Qwen2.5-Coder-32B-Instruct \
  --gpu-memory-utilization 0.90 \
  --host 0.0.0.0 --port 8000

3. Run the Interactive Web Dashboard (or CLI)

Web Interface (Live Streaming Dashboard on http://localhost:5080):

dotnet run --project SbomVexAgent -- ui --port 5080
Download Tool

Most Popular

View all →

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    867
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    544
  • 3

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    385
  • 4

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    360
  • 5

    looking-glass

    anonghosty/looking-glass

    CSIRT platform that ingests Shadowserver reports into MongoDB and replays them as interactive maps, analysis, findings, advisories and executive dashboards.

    302
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    279

Explore all tools

Browse our collection of tools

View all tools →