Swagup

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill is a plausible SwagUp integration, but it gives an agent broad authenticated Membrane/API powers, including write and delete requests, without clear guardrails.

Install only if you trust Membrane and intend to give it access to your SwagUp account. Before allowing the agent to make changes, ask it to show the exact action, endpoint, method, and request body, and require explicit approval for any create, update, or delete operation.

Findings (5)

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 mistaken or hijacked instruction could cause the agent to create, change, or delete SwagUp business data such as orders, shipments, products, or account-related records.

Why it was flagged

This exposes a broad authenticated raw API escape hatch, including mutating and deleting methods, without visible instructions to require user confirmation, limit endpoints, or prefer safer scoped actions for high-impact changes.

Skill content
When the available actions don't cover your use case, you can send requests directly to the SwagUp API through Membrane's proxy... HTTP method (GET, POST, PUT, PATCH, DELETE).
Recommendation

Require explicit user approval for all POST, PUT, PATCH, and DELETE requests, use least-privilege SwagUp/Membrane access, and prefer specific listed actions over raw proxy calls.

What this means

The agent may be able to act with the connected SwagUp account's permissions.

Why it was flagged

The skill requires delegated Membrane/SwagUp authentication and persistent credential refresh. This is expected for the integration, but users should understand the account authority being granted.

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

Connect only the intended account, review granted permissions, and revoke the Membrane/SwagUp connection when no longer needed.

What this means

Future CLI versions could behave differently from the reviewed instructions.

Why it was flagged

The setup uses an unpinned latest npm package installed globally. This is disclosed and central to the skill, but the exact code may change over time.

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

Install from the official package source, consider pinning a reviewed CLI version, and avoid running the setup with unnecessary system privileges.

What this means

SwagUp request data and account access are mediated by Membrane rather than going directly from the user to SwagUp.

Why it was flagged

SwagUp API traffic and authentication handling pass through Membrane as a gateway. This is disclosed and purpose-aligned, but it is still a sensitive data boundary.

Skill content
send requests directly to the SwagUp API through Membrane's proxy. Membrane automatically appends the base URL... and injects the correct authentication headers
Recommendation

Review Membrane's security and privacy posture, and avoid sending unnecessary sensitive data through proxy requests.

What this means

Users may overestimate or misunderstand the specific data scope before connecting an account.

Why it was flagged

The description names CRM-style objects while the overview describes SwagUp swag, shipment, order, product, and warehouse objects. This mismatch could confuse users about what data the skill can affect.

Skill content
description: SwagUp integration. Manage Persons, Organizations, Deals, Leads, Projects, Activities and more... SwagUp is a platform for creating, storing, and distributing branded swag.
Recommendation

Inspect the action list and confirm the target SwagUp object before allowing any write or delete action.