Slack permission, in plain English

What can an AI agent do with
Send messages?

Lets the agent post, edit, schedule, and delete messages in Slack. With a bot token, messages come from the app. With a user token, they look like they came from you.

How to spot it

On a Slack connection or settings screen, this is chat:write.

Strongest thing it allows: Can send as you.

With it, an agent can

  • Post messages in conversations it can reach
  • Edit messages it posted
  • Delete messages it is allowed to delete
  • Schedule messages to post later
  • Show a message that only one person can see

It cannot, on its own

  • With a bot token, post in public channels it was not added to (that needs chat:write.public)
  • With a bot token, delete messages other people posted
  • Read past messages (that needs a separate history permission)

What a bad day looks like

A tricked agent posts a false announcement or a wrong price in a busy channel, and with a user token it looks like you wrote it.

Set it up safer

Ask the company selling the agent

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.