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 Threat Vector Database (TVDB) is CloudsineAI’s proprietary corpus of LLM attack patterns. It powers the Vector Filter layer of ShieldPrompt.

​
What the TVDB contains

  • Curated prompt-injection patterns across direct and indirect injection classes.
  • Known jailbreak templates and their semantic variants.
  • Singapore-context attack patterns observed in CloudsineAI customer telemetry (with explicit customer consent).

​
How the TVDB is maintained

CloudsineAI’s research operation maintains the TVDB on a continuous basis. Emerging attack patterns are surfaced from public-domain disclosures, customer telemetry (consented), and CloudsineAI’s internal research programme, then validated against current Protector Plus detection layers before incorporation.
TVDB feedback loop

​
Cadence

The TVDB updates continuously, with accelerated releases for high-impact disclosures.

​
Domain edge

Two layered moats explain why competitors cannot easily replicate the TVDB’s position.
The TVDB is maintained at a cadence that requires both AI-security depth and red-team engineering capacity — a rare combination.
CloudsineAI’s deployment depth in Singapore Government and SEA regulated enterprise gives the TVDB a sectoral profile that US- and EU-anchored vendors do not currently service.

​
On-prem & air-gapped delivery

In air-gapped deployments, TVDB updates are delivered as signed bundles through the customer’s out-of-band update channel. The management console verifies and imports the bundle into the local vector store and makes it available to the Vector Filter without service interruption.