Back to skill
Skillv1.0.1
ClawScan security
Deliverect · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 22, 2026, 11:17 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions and requirements are internally consistent: it delegates Deliverect work to the Membrane CLI and does not ask for unrelated credentials or system access, though it expects installing/using the Membrane tooling.
- Guidance
- This skill is coherent: it instructs use of the Membrane CLI to manage Deliverect connections and actions instead of directly asking for API keys. Before installing, confirm you trust the Membrane project and the npm package @membranehq/cli (review the npm page and the GitHub repo linked in SKILL.md). Be aware a global npm install modifies your system PATH and may require elevated permissions. The SKILL.md expects network access and a Membrane account; you will need to complete an interactive auth flow (browser or code-based) to create a Deliverect connection. If you prefer not to install global CLIs or to delegate auth to a third party, do not install this skill.
Review Dimensions
- Purpose & Capability
- okThe skill declares itself as a Deliverect integration and all runtime instructions are about using the Membrane CLI to create a Deliverect connection and run actions. Requests (connect, action list/run) align with the stated purpose. Minor note: the registry metadata lists no required binaries while the SKILL.md expects npm/npx and network access (the SKILL.md does state 'Requires network access and a valid Membrane account').
- Instruction Scope
- okInstructions stay on-topic: they tell the agent/operator to install and use the Membrane CLI, authenticate via Membrane, create connections, list and run actions. The SKILL.md explicitly advises not to ask users for Deliverect API keys and to let Membrane manage auth. It does not instruct reading unrelated files, asking for unrelated credentials, or sending data to unexpected endpoints.
- Install Mechanism
- noteThe SKILL.md recommends 'npm install -g @membranehq/cli@latest' (and uses npx in examples). Installing a global npm CLI is a normal but moderately privileged operation (writes to system PATH, may require admin privileges). This is expected for a CLI-driven integration, but users should verify the @membranehq/cli package and trust the publisher before global install.
- Credentials
- okNo environment variables, credentials, or config paths are requested by the skill manifest. The runtime instructions rely on Membrane's server-side auth flow rather than collecting API keys locally, which is proportionate to the claimed purpose.
- Persistence & Privilege
- okThe skill does not request persistent 'always' inclusion and does not indicate it will modify other skills or system-wide agent settings. Autonomous agent invocation remains enabled by default (normal for skills) but is not combined with unusual privileges here.