Knowledge Layer Powering All SILENTCHAIN Products

RAG Security
Knowledge Engine

Generic LLMs hallucinate vulnerabilities. The RAG Security Knowledge Engine grounds every AI finding in 80,000+ real-world security documents — Exploit-DB, CWE, CVE, OWASP, Nuclei templates, and your own scan history. Zero guesswork.

80K+
Knowledge Base Documents
25+
Knowledge Sources
10
Severity Escalation Rules
4
Products Integrated

AI Without Context Is Guessing

LLMs trained on general data lack the depth to reliably assess real-world vulnerabilities. RAG closes that gap with grounded retrieval from curated security knowledge.

Generic LLM Analysis

Standard AI models hallucinate vulnerability names, invent CVE numbers, and generate plausible-sounding but incorrect remediation advice. Confidence scores are unanchored. No memory of what has been seen before or what exploits actually exist in the wild.

RAG-Grounded Analysis

Every finding is backed by real Exploit-DB entries, CWE definitions, CVE records, and Nuclei templates retrieved at inference time. Confidence is calibrated against known exploitability data. Findings link back to primary sources.

Siloed Security Tools

Web scanner finds SSRF. Code scanner finds unsafe deserialization. Network scanner finds open internal ports. Each tool reports in isolation — the critical attack chain connecting them goes undetected.

Cross-Product Correlation

The RAG engine ingests context from every scan surface — web traffic, source code, and network topology. 10 severity escalation rules automatically detect attack chains that span multiple tools and promote findings accordingly.

How RAG Grounds Every Finding

Four-stage pipeline: from raw AI detection to knowledge-verified, severity-calibrated findings with primary source references.

1

AI Detection

LLM identifies a potential vulnerability in web traffic, source code, or network scan output.

2

RAG Retrieval

ChromaDB vector search queries 80K+ docs for CWE definitions, known exploits, CVEs, and prior findings matching the detection.

3

Enrichment

Retrieved context refines severity, adds exploit references, generates PoC suggestions, and calibrates confidence against real-world data.

4

Feedback Loop

Verified findings boost related KB documents and are re-ingested, making the engine smarter with every confirmed vulnerability.

25+ Curated Security Sources

Every document is chunked, embedded, and indexed in ChromaDB with HNSW for sub-millisecond retrieval. Source priority and hit counts influence ranking.

💾

Exploit-DB

Real exploit source code from the world's largest public exploit archive. Mapped to CVEs with proof-of-concept code.

46,000+ exploits
🛡

CWE Top 25

MITRE Common Weakness Enumeration definitions with detection guidance, examples, and remediation patterns.

25 weakness types
🔍

NVD / CVE

National Vulnerability Database entries with CVSS scores, affected products, and vendor advisories via NVD API v2.0.

CVE records

Nuclei Templates

ProjectDiscovery Nuclei detection templates with matchers, extractors, and severity classifications.

Templates
🌐

OWASP Top 10

Complete OWASP Top 10 categories with attack vectors, security weakness descriptions, and prevention cheat sheets.

10 categories
💣

PayloadsAllTheThings

Curated payload collections for XSS, SQLi, LFI, SSTI, XXE, command injection, and 60+ other attack categories.

623+ docs
📄

SecLists

Daniel Miessler's SecLists payloads organized by attack type: XSS, SQLi, LFI, CMDi, SSTI, and XXE.

Payload sets
🔎

Nmap NSE Scripts

Nmap vulnerability detection scripts with service fingerprinting and version-based vulnerability checks.

231 scripts
📊

Your Scan History

Sn1per loot, SILENTCHAIN findings, and SOURCE reports are continuously ingested. Your data trains your engine.

Continuous

See RAG In Action

When AI detects a potential vulnerability, the RAG engine retrieves relevant knowledge in real time to verify, enrich, and calibrate the finding.

  • Vector similarity search across 80K+ documents
  • Sub-millisecond retrieval via ChromaDB HNSW index
  • Source-weighted ranking (Exploit-DB > generic docs)
  • Hit count boosting from verified findings
  • Automatic confidence calibration against known exploits
  • Primary source links in every finding report
rag-engine — live retrieval
[DETECT] AI flags potential SQL Injection in /api/users?id=
[QUERY] Searching KB for: "SQL injection parameter injection"
 
CWE-89 SQL Injection (relevance: 0.94)
EDB-51234 SQLi via user ID param (relevance: 0.91)
CVE-2024-3217 Parameterized query bypass (relevance: 0.87)
nuclei:sqli-error-based Detection template (relevance: 0.85)
 
[ENRICH] Severity: HIGH (confirmed by 3 exploit references)
[ENRICH] Confidence: 0.94 → Certain (calibrated against CWE-89)
[ENRICH] PoC suggested from EDB-51234 payload pattern
 
[FEEDBACK] ✓ Verified — boosting 4 KB docs, ingesting finding

Attack Chains That
Span Products

The RAG engine ingests context from web traffic (Enterprise), source code (SOURCE), and network topology (Sn1per). When findings from multiple products converge on the same target, 10 severity escalation rules automatically detect compound attack chains.

  • Surface context ingestion: URLs, parameters, WAF detection
  • Code context ingestion: file paths, sinks, data flows
  • Network context ingestion: ports, services, technologies
  • Multi-product corroboration escalates to Critical
CRIT SSRF + internal service access detected across web + network scans
CRIT Cloud metadata endpoint reachable via SSRF chain
CRIT RCE confirmed with no WAF protection on target
CRIT Multi-product corroboration: 3+ tools confirm same vulnerability
HIGH SQLi in code + active exploitation in web traffic
HIGH Auth bypass in source + session handling weakness in traffic
HIGH XSS + missing HttpOnly/Secure cookie flags
HIGH File upload + code execution path confirmed in source
HIGH LFI + sensitive file paths found in network scan
HIGH Deserialization sink in code + untrusted input in traffic

A Knowledge Base That Gets Smarter

Every verified finding feeds back into the knowledge base. The more you scan, the better your engine gets.

Powering Every SILENTCHAIN Product

The RAG engine is the shared knowledge layer under all four products. One knowledge base. One feedback loop. Four attack surfaces.

🌐

SILENTCHAIN Enterprise

Async RAGClient for web app scanning. Surface context ingestion + finding correlation.

DAST
💻

SILENTCHAIN SOURCE

Code context ingestion. File paths, sinks, and data flows feed the correlation engine.

SAST
🔌

SILENTCHAIN Pro

Jython HTTP bridge to RAG API. Traffic context + finding correlation from Burp Suite.

Burp Extension
🖧

Sn1per AI Core

Network context ingestion. Ports, services, and technologies enrich the correlation graph.

Network

Full REST API

FastAPI backend with OpenAPI docs. Query the knowledge base, ingest custom data, submit feedback, and run cross-product correlations programmatically.

  • POST /analyze — AI-augmented vulnerability analysis
  • POST /retrieve — Query knowledge base by vector similarity
  • POST /enrich — Enrich finding with KB context
  • POST /ingest — Add custom documents to KB
  • POST /feedback — Submit finding verification feedback
  • POST /correlate — Cross-product attack correlation
  • POST /ingest/context — Ingest target context
  • GET /status — Engine health + document count
  • GET /correlate/context/{target} — Target context
  • DEL /knowledge/{id} — Remove KB document
curl — /retrieve
# Query the knowledge base
$ curl -X POST http://localhost:8000/retrieve \
  -H "Content-Type: application/json" \
  -d '{"query": "SQL injection", "top_k": 5}'
 
{
  "results": [
    {
      "source": "CWE-89",
      "relevance": 0.94,
      "content": "Improper Neutralization of Special Elements used in an SQL Command...",
      "hit_count": 147,
      "verified": true
    },
    {
      "source": "exploit-db:51234",
      "relevance": 0.91,
      "content": "SQLi via unparameterized user ID...",
      "hit_count": 89
    }
  ],
  "total_docs": 80764,
  "query_time_ms": 12
}

Ground Your AI in
Real Security Knowledge

The RAG Security Knowledge Engine is included with SILENTCHAIN Enterprise and SOURCE. Start scanning with 80,000+ documents backing every finding.

Get Enterprise Access Explore SOURCE → Read the Blog Post →
FROM THE BLOG

Related Articles

RAG

Why RAG Changes Everything for AI Vulnerability Scanning

Read more →
Engineering

Building a RAG Pipeline for Vulnerability Detection

Read more →
Correlation

Building an Attack Chain Engine: Cross-Product Vulnerability Correlation

Read more →