Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Moonclerk
v1.0.2MoonClerk integration. Manage Persons, Organizations, Deals, Leads, Projects, Activities and more. Use when the user wants to interact with MoonClerk data.
⭐ 0· 113·0 current·0 all-time
byVlad Ursul@gora050
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's stated purpose (MoonClerk integration) aligns with the instructions (use the Membrane CLI to connect and proxy MoonClerk API calls). However the metadata lists no required binaries or install steps while the runtime instructions explicitly require installing @membranehq/cli (npm) and running membrane commands. The omission of required binaries (npm/membrane) in the metadata is a mismatch.
Instruction Scope
The SKILL.md stays on-topic: it tells the agent how to discover actions, run them, and proxy raw API requests via Membrane. It does not instruct reading unrelated local files or additional environment variables. It does, however, instruct interactive/browser-based login and running networked CLI commands — expected for this integration but significant for user privacy and trust.
Install Mechanism
There is no formal install spec in the registry, while SKILL.md tells users to run an npm global install (npm install -g @membranehq/cli). Installing a global npm package requires elevated permissions on some systems and pulls code from the public npm registry; the skill metadata should declare this requirement. The lack of an explicit install declaration is an inconsistency and increases operational risk.
Credentials
The skill requests no local environment variables or credentials (it explicitly advises against asking users for API keys), which is proportionate. However, it delegates authentication and request proxying to the Membrane service — meaning user data and API requests will transit through and be processed by Membrane's servers. That delegation is not inherently wrong but is a privacy/third‑party trust consideration the user should be aware of.
Persistence & Privilege
The skill is not marked always:true and is user-invocable; it does not request elevated persistent privileges or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other high-risk flags here.
What to consider before installing
Before installing: be aware this skill expects you to install the Membrane CLI (npm install -g @membranehq/cli) and to authenticate via a browser flow — installing a global npm package may require admin rights. The skill delegates auth and API proxying to Membrane, so your MoonClerk requests and data will transit Membrane's service; review Membrane's privacy/security documentation and confirm you trust that third party. The registry metadata is missing declared requirements (npm/membrane CLI); ask the publisher to update the metadata or verify the @membranehq/cli package on the npm registry and the repository (https://github.com/membranedev/application-skills) before proceeding. If you want lower risk, run the CLI inside an isolated environment (container/VM) and avoid granting excessive host permissions.Like a lobster shell, security has layers — review code before you run it.
latestvk979ka960tp7yb6e3pjnhaaf6d842mem
License
MIT-0
Free to use, modify, and redistribute. No attribution required.