Dbt Cloud

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This looks like a coherent Dbt Cloud integration through Membrane, but it relies on delegated credentials, an external CLI, and admin-capable Dbt Cloud actions that users should control carefully.

Before installing, make sure you trust Membrane and the npm CLI package. Use a least-privileged Dbt Cloud account, review authentication scopes, and require explicit confirmation before creating service tokens, webhooks, projects, environments, or groups.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

The Membrane CLI will run locally with the user's permissions, so users must trust the npm package and its future updates.

Why it was flagged

The skill asks the user to install a global CLI from npm using the moving @latest tag. This is disclosed and central to the integration, but it means the installed code can change over time.

Skill content
npm install -g @membranehq/cli@latest
Recommendation

Install only from the trusted Membrane npm package, consider pinning a reviewed version, and use an isolated environment if possible.

What this means

A connected Membrane account may be able to act on Dbt Cloud resources available to the authenticated user.

Why it was flagged

The integration delegates authentication and credential refresh to Membrane for Dbt Cloud access. This is expected for the stated purpose, but it is sensitive account authority.

Skill content
Membrane handles authentication and credentials refresh automatically
Recommendation

Use least-privileged Dbt Cloud credentials, review requested scopes during authentication, and revoke the Membrane connection when it is no longer needed.

What this means

An agent using this skill could create Dbt Cloud resources such as service tokens if the user authorizes or requests that action.

Why it was flagged

The documented action catalog includes mutating, credential-related Dbt Cloud operations. They fit a Dbt Cloud management integration, but they are high-impact if run on the wrong account or without confirmation.

Skill content
| Create Service Token | create-service-token | Create a new service token in a dbt Cloud account. |
Recommendation

Require explicit user confirmation for token, webhook, project, environment, group, or other mutating actions, and verify the target account before running them.

What this means

Provider-returned setup instructions could influence what the agent does during connection setup.

Why it was flagged

The skill may pass provider-supplied instructions into the agent workflow. This is part of the disclosed Membrane connection setup, but those instructions should remain subordinate to the user's request and normal safety checks.

Skill content
`clientAction.agentInstructions` (optional) — instructions for the AI agent on how to proceed programmatically.
Recommendation

Treat returned agent instructions as untrusted operational guidance: follow them only when they match the user's goal and do not bypass approvals or safety checks.

What this means

Dbt Cloud connection details, action metadata, and results may pass through Membrane's service.

Why it was flagged

Dbt Cloud operations are mediated through Membrane rather than directly through Dbt Cloud. This gateway pattern is disclosed and purpose-aligned, but it adds a third-party trust and data boundary.

Skill content
This skill uses the Membrane CLI to interact with Dbt Cloud.
Recommendation

Use this only if you trust Membrane for the relevant Dbt Cloud data, and review Membrane tenant, connection, and retention settings.