Provider
Leonardo Antonio Carta (Nema)Controller
c/o Emperon Studio GmbH, Sachsenring 51a, 50677 Köln, Deutschland
This notice supplements the Privacy Policy for Nema Crew for the Slack module. It does not repeat what the policy says for all modules. That includes the runtimes (Section 6), pseudonymisation and field masks (Section 7), the framework for modules (Section 11), backups (Section 17.6) and your rights (Section 18).
1. Provider and controller
This module is provided and operated by Leonardo Antonio Carta (sole proprietor), c/o Emperon Studio GmbH, Sachsenring 51a, 50677 Cologne, Germany, support@nema.im. It runs as a separate service on our server in Germany. We are the controller. If you use the module in an organisation, we process the data on behalf of the organisation under the Data Processing Agreement.
Slack is not the provider of this module. Slack processes the data of your workspace under its privacy policy and its contracts with the owner of your workspace.
2. What data the module processes
The module works with your own Slack account, not with a bot. What an agent writes or marks with an emoji appears in Slack under your name. An agent only sees what your account is allowed to see in Slack.
Permissions the module requests from Slack when connecting:
channels:read,groups:read,im:read,mpim:read: read the list of your public and private channels, direct messages and group direct messages with their details;channels:history,groups:history,im:history,mpim:history: read messages in these conversations;im:write: open direct messages;chat:write: send messages in your name;users:read: read the people in your workspace with their profile details;reactions:read,reactions:write: read emoji reactions, add them and remove your own;search:read: search messages your account may see;files:read: find canvases and read their content. Slack grants read access to all files your account may see with it; the module uses it for canvases only and rejects other files without passing on their details or downloading them;canvases:read: search sections in a canvas;canvases:write: create and edit canvases in your name, and set and remove their access for channels and people.
If you connected the module before 19 August 2026, your connection lacks the two permissions for reactions. The module has only requested search:read since 27 October 2026; connections made before that do not have it, and search only works there once you reconnect Slack in Nema. The module has requested files:read, canvases:read and canvases:write since 5 November 2026; for older connections canvases only work after reconnecting. The module has never requested any other permissions.
We only receive data that your Slack account is allowed to see:
- when connecting, your Slack ID, the ID of your workspace and the list of permissions Slack granted;
- channels with ID, name, whether private and whether you are a member, number of members, topic and purpose, and for individual channels also the creation time and the ID of the person who created it;
- messages in channels, threads, direct messages and group direct messages with text, time, sender ID, type of message, in search results also username, channel and link to the message; unread messages with the channel they are in;
- people in your workspace with ID, username, full name, display name, title, whether admin or bot, and time zone. The module does not retrieve email addresses: it does not request the
users:read.emailpermission needed for them and passes no email addresses to the agent; - members of a channel (up to 50) with ID, username and full name;
- reactions to a message with emoji, count and the IDs of the people who reacted;
- canvases with ID, title, time of creation and last change, ID of the person who created it, the channels it is shared in, and link; when reading, the full content with everything in it, such as text, tables, checklists, links and mentions of people (name or ID), and the IDs of its sections; when searching sections, only their IDs;
- for events (Section 3), the message as Slack sends it, with text, sender's name and display name, sender ID, channel, thread and the names of attached files.
The module does not download files other than canvases; it fetches a canvas's content anew from Slack each time it is read (at most 40,000 characters go to the agent). It cannot edit or delete messages, delete whole canvases, transfer ownership of a canvas, create or leave channels, or invite people.
3. What for
Exclusively for the functions of Nema Crew that you use and for the tasks that you or members of your organisation give an agent. The agent acts on your behalf with the permissions you granted Slack:
- reading: list channels and their members, fetch details of a channel, read the latest messages of a channel, a thread or direct messages with a person, fetch unread messages, search messages, look up and search people, read reactions, find and read canvases and search sections in them;
- writing: write messages to a channel or thread, send a person a direct message, react with an emoji and remove your own reactions, create canvases (for yourself, as a tab in a channel or as the channel canvas), add to them, replace or delete sections, rename them and share them with channels or people or take that access back.
When you refer to a channel, a person or a direct message with @slack: in the app, the module looks up matching entries (name, username, title, ID).
Triggers: Slack sends us new messages from your account's conversations as soon as they are written. Which conversations these are depends on the events subscribed in Nema Crew's Slack app; at most, they are new messages in public and private channels, direct messages and group direct messages that your account may read (event types message.channels, message.groups, message.im and message.mpim, covered by the …:history permissions above). Messages from bots and notices about edited or deleted messages are discarded on receipt without being stored. We put every other such message into our queue, even if no agent is set up for a trigger, and only then check whether it matches one of these triggers:
- Mentioned in a channel: someone writes @you in a channel, outside a thread;
- Direct message received: someone writes to you in a one-to-one conversation;
- Reply in a thread: someone replies in a thread you started, are mentioned in or have written in yourself. To find out whether you have written in a thread, the module asks Slack (up to 600 messages of the thread).
If a message matches and you have set an agent to the trigger, we start the agent with that message. Messages from bots, your own messages and messages from another workspace trigger nothing. In an organisation, the organisation can block such triggers for the module.
4. Whom the data goes to
- to the module's service on our server;
- to Slack, when an agent reads or writes;
- to the people in Slack who see a message, reaction or canvas that an agent writes in your name, meaning the members of the channel, the person in a direct message or everyone with access to the canvas. Whether Slack notifies them is governed by Slack;
- as a result or event to the language model of the runtime you chose, to the extent an agent needs the data for the task (Privacy Policy Section 6). In the Nema runtime these are the service providers we specify with each request, as our processors (Sections 6.1, 15 and 16). In the Claude Code and Codex runtimes these are Anthropic or OpenAI under your own contract (Sections 6.2 to 6.4);
- to other members and agents in the channel in Nema Crew in which an agent uses the data;
- to Apple's or Google's push service, to the extent the data is in the first 180 characters of a message we send you as a notification (Section 12);
- to the data centre operator on whose hardware our server runs and where our backups are kept, as our processor (Sections 17.6 and 20);
- to authorities only if we are legally obliged to.
The module uses no further service providers.
Countries outside the EU: According to Slack's privacy policy, Slack Technologies Limited (Dublin, Ireland) is responsible for workspaces outside the USA and Canada; for the content of your workspace, Slack is the processor of the workspace owner. Slack also processes data in the USA and other countries (including Australia, Canada, Japan, India and South Korea) on the basis of standard contractual clauses (Art. 46 GDPR); Slack Technologies, LLC is also certified under the EU-US Data Privacy Framework through Salesforce, Inc. (Art. 45 GDPR). For the service providers of the runtimes, Section 16 of the Privacy Policy applies.
Slack's own use: Under its own terms, Slack does not use customer data to train generative AI models without affirmative consent; it does use it by default for non-generative machine learning models, and the workspace owner can opt out. Slack governs this with the owner of your workspace, not Nema. Details are in Slack's privacy policy.
5. Storage and protection
- Credentials: We store your account's Slack token together with your Slack ID, the workspace ID and the granted permissions encrypted (AES-GCM) in our database. The module receives it from our server with each call and does not store it itself.
- Content: The module does not store content from Slack. It fetches it anew with each request. What an agent makes of it, meaning responses, memories, knowledge entries, the steps of its run and the card for a message that triggered it, we store like other content (Privacy Policy Sections 4 and 5).
- Queue: Messages that Slack sends us as events are kept encrypted (AES-GCM) in our queue. We delete processed entries after 7 days and those that could not be processed after 30 days. This also applies to messages that do not trigger an agent, for example because they concern no one or no agent is set up for the trigger. Messages from bots and notices about edited or deleted messages do not go into the queue.
- Cache: Whether you have written in a thread we remember, with the IDs of workspace, channel and thread, for up to 24 hours, a "no" for up to 60 seconds. It contains no content.
- Transmission: The connection to Slack and between your apps and our server is encrypted with TLS. We check events from Slack against their signature before processing them.
- Pseudonymisation: In organisations that have switched on pseudonymisation, the module's results and the messages that trigger an agent go to the language model pseudonymised, unless the organisation has switched this off for the module. For messages that trigger an agent, the organisation can hide or replace individual fields with field masks: the sender's name, display name and ID, the text, the channel and the names of attached files. Both are off by default, and pseudonymisation has limits (Privacy Policy Section 7).
6. Retention, disconnecting, revoking
- Disconnecting: If you disconnect the module in the app, we delete the credentials from our database immediately. After that, no agent retrieves data from this Slack account any more, and messages from Slack no longer trigger an agent. If an Admin or Owner connected the account for an organisation, only the organisation can disconnect it.
- Revoking access at Slack: In Slack you can remove the Nema Crew app or withdraw its authorisation in your workspace's app management; the owner or an admin of your workspace can do so too. The token stored with us then becomes invalid. We remove it from our database when you disconnect in the app or delete your account. Disconnecting in the app does not revoke the token at Slack. It remains valid there until you revoke it yourself. We therefore recommend doing both.
- What remains: What an agent has taken over from Slack into messages, memories or knowledge entries remains stored after disconnecting until you delete it (Privacy Policy Section 17.1). Messages, reactions and canvases an agent wrote in your name stay in Slack.
- Deleting your account: With your account we immediately delete your credentials and content (Privacy Policy Section 17.5). Accounts connected for an organisation remain until the organisation disconnects them or is deleted.
- Backups: The data, including the encrypted token, remains in our backups for up to about 6 months (Privacy Policy Section 17.6).
7. Legal basis
Art. 6(1)(b) GDPR, because the module carries out the connection you set up. For third parties' data, such as messages, names and profile details of colleagues and customers in your workspace, Art. 6(1)(f) GDPR applies, limited to the task you give the agent and to the conversations your account is allowed to see anyway. In organisations we process on their behalf (Privacy Policy Section 2). Your confirmation of this notice is not consent. To end the processing, disconnect the module.
Documents
- This notice
- Data Processing Agreement
- Slack Privacy Policy
This notice supplements the general privacy policy for this module. In the app you confirm it before connecting.