Hub Planner

PassAudited by VirusTotal on May 11, 2026.

Overview

Type: OpenClaw Skill Name: hub-planner Version: 1.0.4 The hub-planner skill provides instructions for an AI agent to interact with the HUB Planner API using the Membrane CLI. It covers standard authentication, connection management, and execution of resource scheduling actions. The use of the '@membranehq/cli' and the Membrane proxy is transparently documented as a way to handle credentials securely, and no evidence of malicious intent, data exfiltration, or harmful prompt injection was found in SKILL.md or _meta.json.

Findings (0)

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.

NoteHigh Confidence
ASI01: Agent Goal Hijack
What this means

A remote connection workflow could influence how the agent proceeds during setup.

Why it was flagged

The skill may consume provider-returned instructions for the agent during connection setup. That is useful integration plumbing, but those instructions should remain bounded to the current setup task and not override the user's request.

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

Treat returned agent instructions as untrusted provider data; follow them only when they are clearly related to the user's current Hub Planner connection task.

ConcernMedium Confidence
ASI02: Tool Misuse and Exploitation
What this means

If the agent selects or runs the wrong action, it could change Hub Planner clients, bookings, time entries, resources, or projects.

Why it was flagged

The skill delegates broad action selection and execution to Membrane and lists create/update operations for Hub Planner business data. The provided visible instructions do not add confirmation, scope, or rollback safeguards before mutations.

Skill content
Search using a natural language description ... `membrane action list --connectionId=CONNECTION_ID --intent "QUERY"` ... `Create Booking` ... `Update Project`
Recommendation

Require explicit user confirmation before any create or update action, show the exact target object and fields, and prefer read/list actions unless the user clearly requested a change.

What this means

Installing and using the skill may grant the integration access to organization scheduling and project data in the connected account.

Why it was flagged

The skill requires delegated Membrane/HUB Planner account access and ongoing credential refresh. This is expected for the integration, but it is sensitive authority.

Skill content
Membrane handles authentication and credentials refresh automatically ... `membrane login --tenant --clientName=<agentType>`
Recommendation

Authenticate only the intended account, use least-privilege access where possible, and know how to revoke the Membrane/HUB Planner connection.

What this means

The actual runtime behavior depends on the installed Membrane CLI version and remote connector generation, not just this SKILL.md file.

Why it was flagged

The setup depends on a globally installed moving npm package and potentially generated connector behavior outside the reviewed skill artifact. This is purpose-aligned but not fully captured by the local package contents.

Skill content
`npm install -g @membranehq/cli@latest` ... `If no app is found, one is created and a connector is built automatically.`
Recommendation

Install the CLI from a trusted source, consider pinning a known version, and review Membrane connector details before granting production access.