Skein
Get started

Trust

Skein holds your memory and connects it to the AI tools you already use. That makes security part of the product, not a setting off to the side. This page covers two things: how your memory is protected, and how to reach us if you find a problem.

How your memory is protected

Your memory lives in your own isolated account, protected by row-level security, so one account cannot read another's.

Every tool you connect is an OAuth connection you can revoke at any time. Skein records which tool reached your memory and when, so you can see what each connection has done. See How Do You Trust an AI Memory? for provenance, change history, and access logs.

On Pro and Max, Skein checks each capture for things like passwords and API keys, and holds anything it finds out of your searchable memory until you review it.

Your memory is yours to export at any time, in a portable format, on every plan. Skein is built for portability, not lock-in.

We do not use your memory to train AI models, ours or anyone else's. The full detail is in our Privacy Policy, including how we use privacy-focused usage analytics on the web app.

Your memory is stored in an encrypted database. Supabase encrypts all data at rest with AES-256, including database files, indexes, and backups. Traffic between you and Skein is encrypted in transit. On Max, when you connect your own provider key, that key is stored encrypted.

When you share a namespace with someone, they get read-only access to that one space and nothing else, and you can take it back at any time. See Sharing a Namespace in Skein.

System status

We publish service availability and incident updates at status.getskein.ai. For security vulnerabilities, use the disclosure process below — not the status page.

Vulnerability disclosure policy

Artificer Innovations, LLC welcomes feedback from security researchers and the general public to help improve our security. If you believe you have discovered a vulnerability, privacy issue, exposed data, or other security issues in any of our assets, we want to hear from you. This policy outlines steps for reporting vulnerabilities to us, what we expect, and what you can expect from us.

Safe harbor language on this page is adapted from the disclose.io framework (CC0 1.0).

Systems in scope

This policy applies to digital assets owned, operated, or maintained by Artificer Innovations, LLC for Skein, including:

  • The Skein web app and the getskein.ai website
  • Your personal MCP endpoint and the OAuth connection flow
  • The API that serves the app and connected tools
  • Sign-in and session handling as they appear in Skein

Out of scope

  • Assets or systems not owned or operated by Artificer Innovations, LLC, including Supabase, Amazon Web Services, Stripe, OpenAI, Resend, Kit, and Sentry. Report those to the provider.
  • Anything that needs a stolen or compromised device, a rooted phone, or a network you already control between a person and Skein.
  • Social engineering of Artificer Innovations, LLC staff or other people.
  • Physical access attempts.
  • Denial of service, or high-volume automated testing.
  • Output from automated scanners with no working example of a real problem.
  • Suggestions to add a header or a setting with no demonstrated impact. These are welcome, they are just lower priority.

Vulnerabilities discovered in out-of-scope systems should be reported to the appropriate vendor or applicable authority.

Our commitments

When working with us according to this policy, you can expect us to:

  • Respond to your report promptly, and work with you to understand and validate your report;
  • Strive to keep you informed about the progress of a vulnerability as it is processed;
  • Work to remediate discovered vulnerabilities in a timely manner, within our operational constraints; and
  • Extend safe harbor for your vulnerability research that is related to this policy.

You'll get an automated confirmation as soon as your report reaches us. We aim to follow up personally within five business days, and we'll keep you posted while we work on a fix.

We will credit you by name if you would like that, or keep you anonymous if you prefer.

Skein does not run a paid bounty program right now. What we offer is a quick response, a real fix, and credit if you want it.

Our expectations

In participating in our vulnerability disclosure program in good faith, we ask that you:

  • Play by the rules, including following this policy and any other relevant agreements. If there is any inconsistency between this policy and any other applicable terms, the terms of this policy will prevail;
  • Report any vulnerability you have discovered promptly;
  • Avoid violating the privacy of others, disrupting our systems, destroying data, and/or harming user experience;
  • Use only the official channel below to discuss vulnerability information with us;
  • Provide us a reasonable amount of time to resolve the issue before you disclose it publicly;
  • Perform testing only on in-scope systems, and respect systems and activities which are out of scope;
  • If a vulnerability provides unintended access to data: limit the amount of data you access to the minimum required for effectively demonstrating a proof of concept; and cease testing and submit a report immediately if you encounter any user data during testing that is not yours;
  • You should only interact with test accounts you own or with explicit permission from the account holder; and
  • Do not engage in extortion.

Official channel

Please report security issues via security@getskein.ai, providing all relevant information: what you found, where you found it, and the steps to reproduce. If you have a working proof of concept, include it. The more details you provide, the easier it will be for us to triage and fix the issue.

Safe harbor

When conducting vulnerability research according to this policy, we consider this research to be:

  • Authorized concerning any applicable anti-hacking laws, and we will not initiate or support legal action against you for accidental, good-faith violations of this policy;
  • Authorized concerning any relevant anti-circumvention laws, and we will not bring a claim against you for circumvention of technology controls;
  • Exempt from restrictions in our Terms of Service and/or Acceptable Usage Policy that would interfere with conducting security research, and we waive those restrictions on a limited basis; and
  • Lawful, helpful to the overall security of the Internet, and conducted in good faith.

You are expected, as always, to comply with all applicable laws. If legal action is initiated by a third party against you and you have complied with this policy, we will take steps to make it known that your actions were conducted in compliance with this policy.

If at any time you have concerns or are uncertain whether your security research is consistent with this policy, please submit a report through our official channel before going any further.

Note that the safe harbor applies only to legal claims under the control of Artificer Innovations, LLC, and that the policy does not bind independent third parties.

Last updated June 10, 2026.