Lmnt

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill is broadly an LMNT/Membrane integration, but its stated purpose is inconsistent and it allows broad authenticated API requests, including write/delete operations, without clear scoping guidance.

Before installing, confirm which LMNT service this is meant to connect to and what data it can access. If you use it, prefer listed/discovered actions and require explicit confirmation before any POST, PUT, PATCH, or DELETE proxy request.

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 user or agent may connect the wrong service or grant access under an incorrect understanding of what data the skill manages.

Why it was flagged

This conflicts with the provided skill description claiming the skill manages Leads, Persons, Organizations, Deals, Projects, and Pipelines, making the intended LMNT product and data scope ambiguous.

Skill content
LMNT is an electrolyte drink mix formulated with a salty taste... LMNT Overview - Element - Property - Material - Project - Report - Task - User
Recommendation

Clarify the target LMNT product, API domain, and supported object types before installation or use.

What this means

An agent could make broad account-changing API calls if it chooses the wrong endpoint or method.

Why it was flagged

The skill exposes a raw authenticated API escape hatch with mutating and destructive methods, but does not define approval, scope, or safety checks for high-impact actions.

Skill content
you can send requests directly to the LMNT API through Membrane's proxy... Flag ... HTTP method (GET, POST, PUT, PATCH, DELETE)
Recommendation

Prefer discovered Membrane actions, require explicit user confirmation for write/delete requests, and document safe endpoint boundaries.

What this means

The connected account may remain accessible to the integration until revoked or disconnected.

Why it was flagged

The skill requires delegated account authentication and persistent credential refresh through Membrane, which is expected for the integration but important for users to notice.

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

Use the least-privileged LMNT/Membrane account available and confirm how to revoke the connection.

What this means

The behavior depends on an external package version that may change after the skill review.

Why it was flagged

The skill relies on installing a global npm CLI at the latest version rather than a pinned version. This is coherent with the Membrane workflow, but it leaves the exact installed code outside the reviewed artifact.

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

Verify the Membrane CLI package source and consider using a pinned version in controlled environments.