Skip to content

Security & privacy

Powerful AI requires stronger boundaries.

NEYVOR AI is built on one principle: intelligence proposes, security decides. Below is our intended architecture and the honest status of each part.

Security execution map

Model proposal → independent control → scoped action

Selected request · illustrative scenario

Move 248 files within an approved Documents folder.

Create folders and move 248 files

Independent controls evaluate the proposed plan against granted scope, policy and risk. The model cannot override this boundary.

04 Permission Decision

Explicit approval needed

Awaiting user approval

The folder boundary is valid, but moving 248 files changes its structure. The example waits for the user to review the plan. Nothing executes while approval is pending.

Execution is locked

User review is the next step. No execution or result verification yet.

◆ Planned architecture. Illustrative, not independently verified

Ten principles

How the boundaries are drawn.

  1. 01In Development

    Independent permission enforcement

    The model proposes actions; a separate policy engine decides. The model cannot grant itself access.

  2. 02Research

    AI Intent Compiler research

    Compiling natural-language goals into a restricted, typed action plan that can be checked before execution.

  3. 03In Development

    Tool-execution boundaries

    Each tool runs with explicit inputs, outputs and limits; nothing is implicit.

  4. 04In Development

    Least-privilege access

    Permissions are scoped to specific resources and expire. Broad access is the exception, not the default.

  5. 05Planned

    Privacy-aware cloud routing

    When cloud models are used, policies decide what may leave the device. Choosing cloud means data is sent to that provider.

  6. 06Research

    Untrusted-content handling

    Web pages, emails and documents are treated as data, never as instructions with authority.

  7. 07Research

    Prompt-injection defence

    Layered mitigations reduce risk. No approach today fully prevents prompt injection, and we don't claim otherwise.

  8. 08Planned

    Action verification

    After execution, outcomes are checked against the approved plan.

  9. 09Planned

    Reversible operations

    Supported changes can be undone. Not every action is reversible, and the interface says so before you approve.

  10. 10Planned

    Auditability and user control

    A readable history of proposals, decisions and actions, owned and visible to you.

Scoped identity

Agents carry a passport, not a master key.

AI Action Passport

NV-PASS · 7F3A-21C9

Agent Identity
file-organiser · v0.1
Allowed Capabilities
list, create-folder, move
Resource Scope
~/Documents (no subfolder escape)
Permission Expiry
15 minutes after approval
Risk Level
Medium (approval required)
Execution Status
Awaiting your approval
Scope is fixed at issue. The agent cannot silently expand its own permissions; any change requires a new passport and your approval.

What we don't claim

  • No security certifications have been obtained yet.
  • No independent audits or penetration tests have been published.
  • No system is immune to prompt injection or attack.
  • Cloud mode is not offline; data goes to the chosen provider.

Found a vulnerability? Please report it responsibly via our contact page.