← Back to Skills Marketplace
New Sloth
by
Vlad Ursul
· GitHub ↗
· v1.0.3
· MIT-0
215
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install new-sloth
Description
New Sloth integration. Manage Organizations. Use when the user wants to interact with New Sloth data.
Usage Guidance
This skill is basically an instruction set for using the Membrane CLI to talk to a New Sloth connector — that is coherent. Before you install/run it: 1) Verify you trust the @membranehq/cli npm package and the homepage (getmembrane.com). 2) Prefer installing a pinned version (not @latest) or inspect the package contents before a global install; npx @latest fetches code on each run and can change behavior unexpectedly. 3) Expect the CLI to persist some auth state locally despite the doc's 'no local secrets' wording — if you need to minimize local credentials, run in a sandbox or ephemeral environment. 4) If you are security-conscious, audit the npm package (or run it in an isolated container) and confirm the connector's source before granting access to production data. If you want, I can list concrete commands to inspect the npm package before installing or suggest safer alternatives (e.g., run the CLI inside a container).
Capability Analysis
Type: OpenClaw Skill
Name: new-sloth
Version: 1.0.3
The skill bundle provides instructions for an AI agent to interact with the Membrane CLI to manage integrations for a service called 'New Sloth'. The instructions in SKILL.md cover standard procedures for installing the '@membranehq/cli' npm package, authenticating, and executing actions through the Membrane platform. No evidence of data exfiltration, malicious code execution, or harmful prompt injection was found; the logic is consistent with the stated purpose of using a third-party integration tool.
Capability Assessment
Purpose & Capability
The name/description (New Sloth integration) aligns with the instructions: all runtime actions use the Membrane CLI to connect to a 'new-sloth' connector, list/discover actions, create actions, and run them. Requiring a Membrane account and network access is reasonable for this purpose.
Instruction Scope
SKILL.md instructions stay within the stated purpose (install Membrane CLI, login, connect, discover/run actions). They do not instruct reading arbitrary system files or exporting unrelated credentials. However, the doc's claim that 'Membrane manages the full Auth lifecycle server-side with no local secrets' conflicts with the explicit interactive login flow (membrane login / login complete) which typically involves local CLI state; the instructions also encourage using npx/@latest which fetches code at runtime.
Install Mechanism
There is no formal registry install spec, but the SKILL.md tells users to run `npm install -g @membranehq/cli@latest` and uses `npx @membranehq/cli@latest`. Installing or fetching unpinned packages from npm (and global installs) is a moderate risk: npm packages can execute arbitrary code and @latest allows silent changes over time. The instruction to perform global installs/frequent dynamic fetches increases the attack surface.
Credentials
The skill declares no required env vars or credentials in registry metadata, and the doc explicitly advises not to ask users for API keys (use Membrane connections instead). That is proportionate. But the doc's assurance of 'no local secrets' is misleading given the CLI login flow; the CLI will likely persist credentials/tokens locally or require the user to complete auth flows — users should assume local credential material may be written by the CLI.
Persistence & Privilege
Registry flags are normal (always:false, user-invocable:true, model invocation enabled). The skill does not claim or request persistent system-wide privileges. The only persistence risk is from the Membrane CLI itself (it may store tokens/config locally), which is outside the skill's direct registry footprint.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install new-sloth - After installation, invoke the skill by name or use
/new-sloth - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
Auto sync from membranedev/application-skills
v1.0.2
Revert refresh marker
v1.0.1
Refresh update marker
v1.0.0
Auto sync from membranedev/application-skills
Metadata
Frequently Asked Questions
What is New Sloth?
New Sloth integration. Manage Organizations. Use when the user wants to interact with New Sloth data. It is an AI Agent Skill for Claude Code / OpenClaw, with 215 downloads so far.
How do I install New Sloth?
Run "/install new-sloth" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is New Sloth free?
Yes, New Sloth is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does New Sloth support?
New Sloth is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created New Sloth?
It is built and maintained by Vlad Ursul (@gora050); the current version is v1.0.3.
More Skills