What can an AI agent do with
Read direct messages?
Lets the agent read direct messages. With a bot token, that means DMs with the app. With a user token, it can read your own private DMs.
How to spot it
On a Slack connection or settings screen, this is im:history.
With it, an agent can
- Read past direct messages and replies
- Receive new direct messages as they arrive
It cannot, on its own
- Read group DMs (that needs mpim:history)
- Send messages
What a bad day looks like
With a user token, the agent can read your private one-on-one chats, and a mistake could quote them to the wrong person.
Set it up safer
- Approve it as a bot so it only reads DMs people send to the app
- Avoid the user-token version of this permission
Ask the company selling the agent
- Will it read my personal DMs or only DMs sent to the app?
- Do you store DM content, and for how long?
- Can I delete what you have stored?
Source
Checked against Slack documentation on 2026-09-28. All Slack permissions →
Thinking about a specific agent?
Tell us what it connects to, what it is allowed to do and who approves its work. You get a plain-language label of what it can touch and what to ask the seller. It takes a couple of minutes, and your answers stay in your browser unless you choose to post a test job.
Or have a person go through the AI apps on up to 3 of your business services with you and get a written report, for $249.
This page explains what a permission allows. It does not describe, test or rate any product. Permission details are summarized in our own words from the provider's documentation, linked on the page; providers change their documentation, so check the source before you rely on a detail.