Back to skill
Skillv1.0.1
ClawScan security
Repsly · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 22, 2026, 11:09 PM
- Verdict
- benign
- Confidence
- medium
- Model
- gpt-5-mini
- Summary
- Instructions and requirements are consistent with a Repsly integration implemented via the Membrane CLI; the skill is instruction-only and does not request unrelated secrets or system access, but it relies on an external npm package/service that you should verify before installing.
- Guidance
- This skill is coherent: it tells you to install and use the Membrane CLI to connect to Repsly and does not ask for unrelated secrets. Before installing or running it, verify the @membranehq/cli package on npm (publisher, version, popularity, repo), confirm you trust getmembrane.com/Membrane as the service that will hold your Repsly credentials, prefer using npx for one-off runs or pin a specific CLI version instead of @latest, and review any permissions presented during the Membrane login flow. If you need stronger assurance, inspect the Membrane CLI repository and audit its login/connection behavior before granting access to your Repsly account.
Review Dimensions
- Purpose & Capability
- okThe skill claims to integrate with Repsly and its instructions use the Membrane CLI to create connections and run actions against Repsly — this aligns with the stated purpose. No unrelated credentials or binaries are requested.
- Instruction Scope
- okSKILL.md confines runtime actions to installing/using the Membrane CLI, logging in, creating a Repsly connection, discovering and running actions. It does not instruct reading local config files or unrelated environment variables.
- Install Mechanism
- noteNo registry install spec is provided, but the instructions tell the user to run 'npm install -g @membranehq/cli@latest' (or use npx). Installing an npm CLI is a common pattern but pulls code from the public npm registry — a moderate-risk action that should be verified (package identity, publisher, version).
- Credentials
- okThe skill declares no required env vars or credentials and explicitly advises against asking users for API keys. Authentication is delegated to Membrane via an interactive login flow, which is proportionate for this integration.
- Persistence & Privilege
- okThe skill is instruction-only, has always:false, and does not request persistent agent-level privileges or modifications to other skills. Autonomous invocation is allowed by default (normal) and does not combine with other concerning privileges.