The security model

Safe to run because of how it's built, not because we promise.

Selam is an autonomous agent with real reach — messaging, email, your files. That's exactly why every layer below exists. This page is the whole model, stated plainly, for people who read pages like this one.

Last updated · July 2026
01

Nothing is listening on the internet.

Selam runs entirely on your Mac. Her internal server binds to loopback only — there is no public port, no hosted dashboard, no cloud instance with your agent behind a login page. The wave of exposed agent deployments found scanning the internet in 2026 is a category of problem Selam doesn't have: there's nothing to find because nothing is reachable.

02

Every action is tiered before it runs.

The brain doesn't get raw tool access. It emits structured actions, and a dispatcher classifies every one of them against a fixed trust table before anything executes:

T0

Silent internal work — reading files she owns, checking her own task list. Runs without ceremony.

T1

Local, reversible effects — writing a note, packaging an export on your own disk.

T2

Outward-facing but recoverable — a message to a contact you've explicitly trusted. Dry-run capable, logged.

T3

Irreversible or public — money movement, email to a human, posting publicly. Waits for your spoken yes. Always.

Tiering is enforced in the dispatch layer, not suggested in a prompt — a jailbroken model can ask for whatever it wants; the dispatcher still gates it.

03

Spend is capped at four levels.

A runaway loop hits a wall measured in cents. And a task that fails three runs in a row pauses itself and tells you — it doesn't keep hammering, and it doesn't quietly disappear.

04

Skills are signed, or they don't load.

Agent "skills" are the supply-chain attack surface of this product category — in January 2026, researchers found hundreds of malicious skills on a popular open agent hub, some designed to exfiltrate credentials. Selam's answer is a signed first-party catalog:

05

She never claims what she didn't see.

An agent that reports success it never verified is worse than one that fails loudly. Selam's dispatch layer treats claims as observations:

06

Your keys, your data, your exit.

The honest part

No local agent can be made risk-free, and we won't pretend otherwise. Selam executes real actions with real credentials; the layers above are how we bound the blast radius of a bad model output, a prompt injection, or a malicious skill. If you find a hole in any of them, we want to know — see below.

07

Found something? Tell us.

Security reports go to selam@atxo.me. We read everything, respond to real findings fast, and credit reporters who want credit. Please give us a reasonable window to ship a fix before publishing.