Vetta
Reference

08 / REFERENCE

Security and data boundaries

Understand the data flow between local workspaces, model requests, credentials, MCP, plugins, and execution permissions.

Vetta centers work in a local workspace, but “runs locally” does not mean that all content stays on the device. Model providers, MCP, and plugins may send task data to configured external services. Understand each boundary before using it.

Data flow overview

Local workspaceProject files, sessions, knowledge sources, and configuration
→
Context assemblyTask, citations, tool results, and capability instructions
→
Selected model serviceThe context required for this invocation

Local tools may continue to read or modify files. MCP, plugins, webhooks, and IM channels can create separate external requests.

Responsibility by boundary

BoundaryData it may seeYour check
Model providerPrompt, citations, history, tool results, and imagesProvider, base URL, model, and privacy terms
Local toolsWorkspace files, command output, and processesSandbox or full access, target path, and command
MCPTool arguments and external results, OAuth or token metadataSource, transport, and auto-approval scope
PluginManifest-declared UI, file, network, or Agent capabilitiesSource, permissions, version, and enabled state
Knowledge baseImported sources, processed results, and retrieved excerptsProcessing model, import scope, and deletion semantics
Webhook / IMNotification content, conversation, or attachment metadataDestination, channel credentials, and sharing scope
Paired phoneSession text, attachments, the desktop picture, and pointer or keyboard inputGive the QR code, connection code, and password only to the intended phone, and remove phones you no longer use. The relay forwards ciphertext only

Credential handling

  • Enter credentials only in dedicated model, MCP, IM, or webhook configuration UI.
  • Do not put keys, tokens, cookies, or authorization codes in tasks, project files, skills, logs, or issue reports.
  • References such as env:MY_API_KEY store only the variable name; the environment that starts Vetta must still protect the value.
  • Inspect diagnostic exports and sessions before sharing them. Do not assume every third-party tool output is automatically redacted.

Execution permissions

Restricted sandbox mode limits file and process access to the workspace capability boundary. Full access permits broader system operations. If a platform cannot provide sandboxing, Vetta explains why; do not treat “sandbox unavailable” as equivalent protection.

A permission prompt only means that the host is asking whether to perform an action. Confirm the target path, command, network address, and reversibility, and do not assume the request itself is trustworthy.

Installing external capabilities

Skills, plugins, MCP servers, and external capability repositories are untrusted inputs. Install only from trusted sources, inspect updates, and grant the smallest permission set that meets the goal. Disable to keep an installation; remove to uninstall it.

On this page