Prompt VaultSurface audit

Prompt Vault surface audit

This page tracks where raw prompt text can move after ingestion and how Prompt Vault keeps protected modes from exposing it through normal evidence flows.

This page tracks where raw prompt text can move after ingestion and how Prompt Vault keeps protected modes from exposing it through normal evidence flows.

Audit result

Prompt Vault has two privacy boundaries:

  1. Retention boundary: Runtime Shield and OTLP apply the selected mode before normal rows are stored.
  2. Surface boundary: Normal JSON, copy, export, preview, and AI-analysis paths re-apply Prompt Vault-safe serialization before rendering or sending retained payloads.

In Sealed Evidence and Promptless, prompt-like fields are replaced with Prompt Vault placeholders in normal surfaces. The governed reveal endpoint remains the only dashboard path that returns sealed prompt text.

Covered surfaces

SurfaceNormal data sourceProtected-mode behavior
Activity feedactivity_feed_page_v2 payloadsServer responses are serialized with Prompt Vault-safe JSON before the table or drawer receives them.
Activity drawer Raw JSON and Export JSONselected Activity event payloadCopy/download uses Prompt Vault-safe JSON. Start-rule evidence handoff also receives the safe payload.
Workstation event cardsshield_events.contextPrompt evidence renders as sealed/not retained, and raw context blocks use safe JSON.
Shield event cardsshield_events.contextMetadata and raw context blocks use safe JSON.
Session timelinegetSessionEventsShield and OTLP event contexts are safe before client rendering.
Prompts & DecisionsOTLP prompt groupsRoute returns safe OTLP events before grouping them for the UI.
Findingsfinding prompt metadataSealed prompts use reveal controls; Promptless has no body to render.
Investigation timeline and evidencealert detail, linked shield events, linked OTLP eventsAlert detail normalizes linked evidence through safe JSON before it reaches the client.
Member timelineshield contextRaw context blocks use safe JSON.
Gateway context blocksMCP contextSafe JSON is applied when Prompt Vault metadata exists. Arbitrary MCP prompt-like parameters need product classification before they become Prompt Vault-governed.
Custom detector preview and dry runbackground Activity/OTLP samplesSample candidates are safe before detector evaluation sees retained context.
Session JSON exportshield_events plus triage/outputExported event context is safe and includes Prompt Vault metadata instead of protected prompt bodies.
Event archiveretained shield_events, events, otlp_events rowsArchived JSONL rows use safe JSON for protected Prompt Vault modes.
AI session analysis and LLM threat reviewshield_events summariesEvent summaries are built from safe event data.
Notifications and exception AI triageredacted evidence packsExisting redaction removes raw prompt/tool fields before outbound notification or AI triage payloads.

What still requires product classification

Prompt Vault currently protects supported prompt-submit events and OTLP prompt fields. Some tools use fields named prompt, message, content, or input as ordinary tool parameters. Those are not automatically treated as raw user prompts unless the event is already marked with Prompt Vault metadata.

The follow-up decision is whether to extend Prompt Vault from prompt events to arbitrary prompt-like tool parameters across MCP Gateway, browser extension events, gateway runtimes, and future connectors.

Verification expectation

Regression tests use canary prompt strings and fail if protected prompt text appears in safe JSON. Sandbox promotion should verify lint, tests, container build, ECR publish, Helm rollout, health checks, policy canary, RLS audit, and optional E2E smoke before production promotion.