Security and data handling changedclaude-tag/concepts/security-and-data
Nearest release: v2.1.283, published 3 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 25 Sep 2026 22:04 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 25 Sep 2026 22:07 UTC.
Upstream edited
Recorded here
Lines+2added
Lines−2removed
From line
67
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits17to this page, all time
The whole hunk
from line 67, old and new numbered
/
from line 67
6767
6868DMs with `@Claude` run on the user's own claude.ai account instead, with that user's personal connectors, and work there is attributed to them, except pull requests, which the Claude GitHub App authors from DMs as well. Owners can disable DMs organization-wide; see [Allow or disable direct messages](/docs/claude-tag/admins/restrict-access#allow-or-disable-direct-messages).
6969
70Personal connectors in channels is available to a limited number of organizations. Where it is available, Claude uses a user's personal connectors in a channel only for that user's own tasks, after the user allows it. The work runs with that user's permissions and is recorded under their name. Requests other people make to Claude in the task's thread run with the channel's own access, not with that user's connectors. Claude is designed to take direction from the connector's owner, treating what other people post in the thread as information for the task rather than as instructions, and the owner can tell Claude in the task's thread to stop. See [Personal connectors in channels](/docs/claude-tag/concepts/personal-connectors).
70With [personal connectors in channels](/docs/claude-tag/concepts/personal-connectors), Claude uses a user's personal connectors in a channel only for that user's own tasks, after the user allows it. The work runs with that user's permissions and is recorded under their name. Requests other people make to Claude in the task's thread run with the channel's own access, not with that user's connectors. Claude is designed to take direction from the connector's owner, treating what other people post in the thread as information for the task rather than as instructions, and the owner can tell Claude in the task's thread to stop. See [Personal connectors in channels](/docs/claude-tag/concepts/personal-connectors).
7171
7272### Isolate credentials between channels
7373
from line 89
8989
9090Claude doesn't work in a channel shared with another company through [Slack Connect](/docs/claude-tag/admins/restrict-access#slack-connect-channels), so no access bundle's credentials reach one.
9191
92Isolating a credential doesn't isolate what Claude knows. What it learns in a public channel becomes [workspace memory](/docs/claude-tag/users/memory) that sessions in the workspace's other channels can read, and it can [search public channels by keyword](/docs/claude-tag/admins/restrict-access#controls-that-aren%E2%80%99t-available) without being added to them, the same way any workspace member can.
92Isolating a credential doesn't isolate what Claude knows. The [workspace notes](/docs/claude-tag/users/memory) it saves from a public channel are read by sessions in every channel of the workspace, and it can [search public channels by keyword](/docs/claude-tag/admins/restrict-access#controls-that-aren%E2%80%99t-available) without being added to them, the same way any workspace member can.
9393
9494## Artifact visibility
9595
No line in this hunk matches that.