Clockwork

ReviewAudited by ClawScan on May 10, 2026.

Overview

Clockwork appears to be a legitimate integration, but it gives the agent broad authenticated Clockwork API access through Membrane, including direct requests that could change or delete data without clear guardrails.

Before installing, be comfortable granting Membrane-mediated access to your Clockwork account. Ask the agent to confirm exact actions before it creates, updates, deletes, or automates records, and consider pinning the Membrane CLI version if you use this in a sensitive environment.

Findings (4)

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

A wrong or overly broad agent request could change or remove Clockwork tasks, time entries, calendar data, or workflow settings.

Why it was flagged

The skill provides a generic authenticated API escape hatch, including mutating and deleting HTTP methods, without visible approval or scoping rules.

Skill content
send requests directly to the Clockwork API through Membrane's proxy ... `-X, --method` | HTTP method (GET, POST, PUT, PATCH, DELETE)
Recommendation

Require the agent to show the exact action, endpoint, method, and record IDs before any POST, PUT, PATCH, DELETE, or workflow automation request.

What this means

Installing and using the skill can let Membrane-mediated commands act with the connected Clockwork account's permissions.

Why it was flagged

The integration uses delegated account access and refreshes credentials through Membrane, which is expected but sensitive.

Skill content
Membrane handles authentication and credentials refresh automatically
Recommendation

Connect only the intended Clockwork account, review granted permissions, and revoke the Membrane connection when it is no longer needed.

What this means

Future CLI package changes could affect what commands do or what data is handled.

Why it was flagged

The setup relies on installing the latest global npm CLI package, which is central to the skill but not pinned to a reviewed version.

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

Install from the official package source and consider pinning a known-good Membrane CLI version in controlled environments.

What this means

Clockwork request data and account access are mediated by a third-party service boundary, which users should understand before connecting.

Why it was flagged

Clockwork API requests and related data pass through a Membrane proxy/gateway that also applies authentication.

Skill content
send requests directly to the Clockwork API through Membrane's proxy ... injects the correct authentication headers
Recommendation

Use this only if you trust Membrane as the integration gateway and avoid sending unnecessary sensitive Clockwork data.