Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Tatum
v1.0.0Tatum integration. Manage data, records, and automate workflows. Use when the user wants to interact with Tatum data.
⭐ 0· 18·0 current·0 all-time
byMembrane Dev@membranedev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
The skill claims to integrate with Tatum and the instructions consistently use Membrane CLI and Membrane connections to reach the Tatum API. Required permissions (network access and a Membrane account) align with that goal and there are no unrelated requirements (no AWS, no unrelated tokens, no filesystem config paths).
Instruction Scope
SKILL.md confines itself to installing/using the Membrane CLI, creating a Membrane connection, listing and running actions, and optionally proxying requests to Tatum via Membrane. It does not request reading local files, exporting unrelated environment variables, or sending data to endpoints outside of Membrane/Tatum. It does recommend global npm installation and browser-based login flows, which are expected for this workflow.
Install Mechanism
There is no platform install spec; the doc recommends using `npm install -g @membranehq/cli`. Because the skill is instruction-only, nothing will be written to disk by the skill bundle itself. The install recommendation is a standard public npm package installation (the SKILL.md points to the official Membrane CLI package), so no unexpected download-from-random-URL behavior is present in the skill materials.
Credentials
The skill declares no required environment variables or credentials. It explicitly instructs to let Membrane manage credentials and not to ask users for API keys. Requesting a Membrane account and the resulting connection is proportionate to a Tatum integration; no unrelated secrets or broad environment access is requested.
Persistence & Privilege
The skill does not request always:true, does not alter other skills or system-wide agent settings in the instructions, and is user-invocable. There is no evidence the skill attempts to persist credentials locally or modify other skill configurations.
Assessment
This skill appears internally consistent: it uses Membrane as an intermediary to talk to Tatum and does not ask for local API keys or weird environment access. Before installing/use: 1) Verify you trust Membrane (https://getmembrane.com) because connections created will be managed server-side by Membrane and have access to your Tatum data. 2) Installing the Membrane CLI globally requires npm and may require elevated permissions — run it in an environment where you control the machine. 3) During `membrane login` you will complete an auth flow in a browser (or use the headless flow); confirm the URL and auth prompt are legitimate. 4) Review Membrane connection permissions/audit logs for any account you authorize. If you need stronger assurance, ask the skill author for an explicit list of the Membrane connector scopes that will be requested when connecting to Tatum.Like a lobster shell, security has layers — review code before you run it.
latestvk9788j1y8phz38vkx3btvwjj3h848g9g
License
MIT-0
Free to use, modify, and redistribute. No attribution required.