> ## Documentation Index
> Fetch the complete documentation index at: https://docs.archetype.ing/llms.txt
> Use this file to discover all available pages before exploring further.

# Security

> What stays on your computer, what leaves it, what the agent may do, and how to report a problem.

## What stays and what leaves

Your conversations, records, memory, settings and keys are kept on your computer. Archetype sends no usage data.

What leaves it is what you set up:

| Goes to | What |
| - | - |
| The engine's model provider | Your messages, and what the agent reads and runs to answer them |
| The web search service (Exa unless you choose another) | The agent's searches |
| Apps and MCP servers you connect | What the agent asks them |
| Chat channels you add | The chats with the agent |
| GitHub and models.dev | The check for a new release, and the model list (`ARCHETYPE_NO_NETWORK=1` stops both) |
| Your company's host | What you do in the company's space, and what you send to it |

## What the agent may do

The agent asks before it edits, runs commands or sends anything, as your [permission mode](https://docs.archetype.ing/en/use/approvals.md) says. A few rules hold whatever the mode:

* A project's config can narrow what the agent may do, never widen it, and a project's named agent cannot replace a built-in one.
* An engine's own settings in a folder (`.cursor/`, `opencode.json` and others) are asked about once before the engine uses them.
* Programs that start other programs (`sh`, `env`, `npm run`, `docker` …) are asked each time, never kept as **Always allow**.

In **Manage → Permissions**:

| Setting | What it does |
| - | - |
| **Action monitor** | Another model checks each call before it runs (by default the ones nobody is there for). A blocked call stops the work until you go on. Off by default. |
| **Engines in a sandbox** | Keeps what each engine writes inside the conversation's folder. Off by default. |
| **Keep my SSH agent from engines** | Engines start without your SSH and GPG agents, so their commands cannot sign as you. |
| **Engines never hold your API keys** | Claude Code and Codex on an API key get a token that works only during their turn; a proxy on your computer adds the key. |

## Secrets

* Keys are in `~/.config/archetype/env`, readable by you only; the app shows a key's name, never its value.
* A key the agent asks for is typed on a card, kept out of the conversation, and saved in `~/.local/share/archetype/secrets/`. The agent can still read that file, so this keeps a key out of the record, not from an agent you do not trust.
* Codex and the other engines get only the keys they sign in with, and those you list in `passEnv`.
* Memory refuses text that looks like a key.

## Plugins

Each plugin's processes run in your system's sandbox. By default a plugin reaches only its own folder and data, and no network. Its manifest declares what more it needs: the network, or your files. `~/.ssh`, `~/.gnupg`, cloud credentials and Archetype's own config and data stay closed to it whatever it declares. Where there is no sandbox (Windows, for one), only Pairful's plugins run.

## A company's host

A company's host keeps the company's conversations, projects and knowledge. Whoever runs the host can read what it keeps. Your own accounts connect in your own Archetype, not on the company's host, and your own subscription runs only your requests there. See [Archetype for Teams](https://docs.archetype.ing/en/teams/overview.md).

## Report a vulnerability

Email [dev@pairful.ai](mailto:dev@pairful.ai), not a public issue. Say the version (`archetype --version`), the system, the steps to reproduce it, and what an attacker gains.

We answer within 5 working days, and say within 15 whether it is a vulnerability and how serious. We fix it in a release and publish an advisory, crediting you unless you ask us not to. For other problems, see [Support](https://docs.archetype.ing/en/support.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.