M
motherduck-security-governance
About motherduck-security-governance
A guidance skill for AI agents handling MotherDuck security and governance questions. It emphasizes checking current public documentation, defining access boundaries, and distinguishing documented guarantees from recommendations.
Key features
- 01Current-documentation verification
- 02Credential and service-account guidance
- 03Data-isolation boundary review
- 04Role and grant analysis
- 05Residency and AI data-flow checks
Use cases
- 01Reviewing a MotherDuck production access design
- 02Evaluating tenant isolation choices
- 03Checking regional data-flow requirements
MCP support
When the MotherDuck MCP `ask_docs_question` feature is available, the skill recommends using it to consult documentation before relying on other sources.
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ motherduckdb/ agent-skills --skill motherduck-security-governanceAfter installing, type/motherduck-security-governancein Claude Code to confirm it loaded.
Bundled filesreferences/SECURITY_GOVERNANCE_PLAYBOOK.md
Details
From the project READMESecurity and Governance
Source Of Truth
- Prefer current MotherDuck public trust, security, pricing, and product documentation.
- If the MotherDuck MCP
ask_docs_questionfeature is available, use it first. - Use current SSO and data-recovery docs when the requirement involves identity-provider login, restore windows, named snapshots, or
UNDROP DATABASE. - Verify claims against live public materials before making compliance or commercial assertions.
Default Posture
- Prefer service accounts for production systems, not personal tokens.
- Keep credentials in backend-controlled secrets, not browsers or hardcoded notebooks.
- Prefer structural isolation over query-time tenant filtering for serious B2B or CFA workloads.
- Treat region and residency as first-class architectural constraints that require current public confirmation.
- Be explicit about whether the boundary is a share, a Dive, a database, or a full application.
- Separate platform permissions (roles), data grants (who can attach a share), include patterns (which tables/views that share exposes), and secure views (which rows, columns, and values each consumer of that share sees).
- Secure views on shares provide row-level security, column-level security, and masking keyed on the consumer's identity or roles (Business and Enterprise). For multi-tenant customer-facing products, structural isolation remains the stronger default; secure views fit internal audiences and partner or per-service-account shares.
- Flight
RUNgrants let others trigger a Flight that always executes with the owner's credentials. Review them like any privileged entry point: who holds the grant, which config the caller controls, and what the owner's token can write. - Map AI data flows explicitly:
prompt_jev()sends text and images to TypeSafe in the US from every region (off by default in EU regions);prompt()from Asia Pacific regions is served by a US endpoint; Agent Chat inference stays in the organization's geography. Admins control these on the AI Features settings page. - Flights are generally available and can process PHI under a signed HIPAA BAA.
- Separate documented product guarantees from architectural recommendations and assumptions in the final answer.
Workflow
- Identify where credentials live and who administers them.
- Define the actual isolation boundary: account, database, schema, share secure view, or query filter.
- Determine which preset/custom roles users hold, who can read, write, share, or administer the data, and which grants actually provide access.
- Check whether residency, compliance, or contractual guarantees are part of the requirement.
- Use only publicly documented security anchors unless the user has current commercial documentation in hand.
References
Read only the reference sections needed for the current task.
- Read
references/SECURITY_GOVERNANCE_PLAYBOOK.mdfor public security anchors, service-account posture, residency and AI data flows, sharing boundaries, Flight run grants, governance as code, and what not to overstate
Related Skills
Load related skills only for missing capabilities; reuse established context.
motherduck-connectfor secure token handling and endpoint selectionmotherduck-explorewhen governance depends on what data is actually present and how it is partitionedmotherduck-share-datawhen the design includes governed data distribution
Comments
Markdown supported