Back to skill
Skillv1.0.3
ClawScan security
Mobile Text Alerts · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 22, 2026, 12:07 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions and requirements are coherent with a Mobile Text Alerts integration using the Membrane CLI; nothing in the SKILL.md asks for unrelated credentials or system access, though the CLI install step is an external action the user should review.
- Guidance
- This skill appears to do what it says: it instructs the agent to use the Membrane CLI to manage Mobile Text Alerts actions and connections. Before installing or running it, verify you trust the @membranehq/cli package (review its npm/github repo), prefer using `npx` or a local install instead of a global `-g` install if you want to reduce risk, and ensure you are comfortable authenticating via Membrane (it handles credentials server-side). If you need stricter controls, run the CLI commands manually rather than granting the agent freedom to execute them automatically.
Review Dimensions
- Purpose & Capability
- okThe skill's name and description (Mobile Text Alerts integration) match the runtime instructions which use Membrane to connect, discover, and run actions against Mobile Text Alerts. The workflow (connect, list actions, run/create actions) is appropriate for the stated purpose.
- Instruction Scope
- okSKILL.md confines itself to using the Membrane CLI for auth, connection management, action discovery, and running actions. It does not instruct the agent to read unrelated files, access unexpected environment variables, or transmit data to endpoints outside of Membrane/Mobile Text Alerts. Headless login flow and JSON flags are documented and scoped to authentication and integration.
- Install Mechanism
- noteThis is an instruction-only skill with no install spec, but the README tells users to run `npm install -g @membranehq/cli@latest` (and suggests `npx` elsewhere). Installing a global npm package executes third-party code and is a moderate-risk action; the SKILL.md does not include a declared install spec in the registry metadata. Verify the @membranehq/cli package source/reputation before installing, or prefer `npx`/local installs if concerned.
- Credentials
- okThe skill does not request environment variables, credentials, or config paths. Authentication is handled via Membrane's interactive login and connection flow, and SKILL.md explicitly advises not to ask users for API keys or tokens. There are no unexplained or unrelated credential requests.
- Persistence & Privilege
- okThe skill is not marked always:true and does not request persistent system-level changes. It does not instruct modifying other skills or global agent configuration. Agent autonomous invocation is allowed (platform default) but not combined with other risky factors.