Back to skill
Skillv1.0.2

ClawScan security

Appwrite · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 2, 2026, 9:06 PM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is an instruction-only wrapper that tells the agent to use the Membrane CLI to interact with Appwrite; its requirements and instructions are coherent with its stated purpose.
Guidance
This skill delegates all Appwrite interactions to the Membrane service via the Membrane CLI. Before installing: (1) verify you trust Membrane because it will handle and proxy credentials and API calls (sensitive data will transit their service), (2) review the @membranehq/cli npm package source and release provenance before running a global npm install, and (3) grant the Membrane connection only the minimal privileges needed for the task. Avoid pasting raw secrets into chat and prefer using the connection flow the CLI provides.

Review Dimensions

Purpose & Capability
okName/description claim Appwrite integration and the instructions exclusively direct use of Membrane to connect to Appwrite, list actions, run actions, and proxy requests. No unrelated services, credentials, or binaries are requested.
Instruction Scope
okSKILL.md only instructs installing the Membrane CLI, logging in, creating/using connections, listing and running Appwrite actions, and optionally proxying raw Appwrite API requests through Membrane. It does not ask the agent to read host files, arbitrary env vars, or exfiltrate data outside the described flow.
Install Mechanism
noteInstall guidance is a single npm global install of @membranehq/cli. npm packages are a common delivery method; this is expected but carries the usual trust considerations for installing global packages (review package source and permissions).
Credentials
okThe skill declares no required env vars or credentials. It requires a Membrane account (handled via the CLI/browser auth flow) which is proportionate to delegating Appwrite auth to Membrane.
Persistence & Privilege
okNo always:true flag and no instructions to modify other skills or system-wide settings. Autonomous invocation is allowed by default but that is normal for skills and not excessive here.