Back to skill
Skillv1.0.2

ClawScan security

Beehiiv · 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 Beehiiv integration that consistently relies on the Membrane CLI for auth and API access; its requirements and instructions match its stated purpose.
Guidance
This skill appears coherent and uses the Membrane CLI to manage Beehiiv connections. Before installing or running commands: (1) verify the @membranehq/cli package on npm/GitHub to ensure it’s the legitimate project; (2) prefer installing the CLI in a controlled environment (container/VM) if you’re cautious about global npm installs; (3) follow the browser OAuth flow—do not paste external API keys into chat; (4) be aware that Membrane can proxy arbitrary API requests for a connected account, so only connect accounts you trust and monitor what actions you run; (5) if you need higher assurance, review the Membrane CLI source or use an organizational process to vet the package before use.

Review Dimensions

Purpose & Capability
okName/description (Beehiiv integration) align with the instructions: the SKILL.md only describes using the Membrane CLI to connect to Beehiiv, list actions, run actions, and proxy requests. No unrelated capabilities, binaries, or unrelated credentials are requested.
Instruction Scope
okRuntime instructions are limited to installing and using the Membrane CLI (login, connect, action list/run, request proxy). The doc does not instruct reading arbitrary files, other environment variables, or exfiltrating data to unknown endpoints; proxying goes to Beehiiv via Membrane, which is expected for this integration.
Install Mechanism
noteNo install spec in the skill bundle itself, but the SKILL.md instructs installing @membranehq/cli via npm (-g). This is an expected way to get the CLI but has the usual npm caveats (installing global packages can run lifecycle scripts). Recommend verifying the package source (npmjs/github) before installing on sensitive machines.
Credentials
okThe skill declares no required env vars or credentials and relies on Membrane's browser-based auth and connection objects. That is proportionate to the stated purpose. The SKILL.md explicitly advises not to ask users for API keys, which is appropriate.
Persistence & Privilege
okThe skill does not request 'always: true' or other elevated installation privileges and is instruction-only. The only persistent effect would be a user-installed CLI binary, which is expected for this workflow.