Skip to main content

Documentation Index

Fetch the complete documentation index at: https://cloudsineai-5cd7c547.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

​
The detection stack

Protector Plus combines two complementary layers in defence-in-depth: deterministic Standard Guardrails for known patterns, and ShieldPrompt for model-driven detection.
1

Standard Guardrails (rule-based, CPU-powered)

Deterministic detection for well-known risk vectors: Keyword Blocklist, Regex Pattern Matching, and PII Detection (NER-based) for inputs and outputs.
2

ShieldPrompt (GPU-powered, defence-in-depth)

The orchestration pipeline combining four model-based layers:
  • LLM Classifier — an LLM-as-judge model that scores prompt-injection likelihood
  • Vector Filter — semantic similarity against the Threat Vector Database (TVDB)
  • Content Moderation — purpose-built classifier for hazardous content
  • System Prompt Protection — detection of system-prompt leakage in LLM responses

​
Security profiles

A security profile is a packaged set of policy configurations. Each GenAI application is bound to a security profile, which determines which guardrails are enabled, in what mode (block or monitor), and with what thresholds.
Start at Protection Level 3 (Standard Protection + ShieldPrompt Preset 2). It enables the LLM, Vector, Content Moderation, and System Prompt Protection guardrails by default. Tune from there.

​
Deployment modes

Protector Plus supports topologies that place either an LLM gateway or the GenAI Firewall as the first hop from the application.
ModeFirst hopEnforcementWhen to use
Gateway-firstLLM gatewayNon-blockingRapid adoption; low app-side change. App interprets findings.
ForwardingGenAI FirewallBlockingProduction with strict policy enforcement.
Non-forwardingGenAI FirewallApp-decidesApp retains final allow/deny authority.
See Deployment Modes for the full flow diagrams.

​
The Threat Vector Database (TVDB)

The TVDB is CloudsineAI’s proprietary corpus of LLM attack patterns. It powers the Vector Filter layer of ShieldPrompt. The TVDB is maintained on a continuous basis by CloudsineAI’s research operation, with accelerated releases for high-impact disclosures. Read more in Threat Vector Database.

​
Glossary

TermMeaning
GenAI FirewallThe Protector Plus runtime inspection service.
ShieldPromptThe defence-in-depth orchestration pipeline (LLM + Vector + Content Moderation + System-Prompt Protection).
TVDBThreat Vector Database — CloudsineAI’s proprietary attack-pattern corpus.
Security profileA packaged guardrail configuration bound to a GenAI application.
Protection levelA templated guardrail preset (Level 0–3 or Full Custom).