Back to skill
Skillv1.0.1

ClawScan security

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

Scanner verdict

BenignFeb 11, 2026, 9:06 AM
Verdict
benign
Confidence
medium
Model
gpt-5-mini
Summary
The skill's instructions and requirements are coherent with a pest‑control booking integration and do not request unrelated system access, but it omits authentication details and includes example personal data — verify the external service and data flows before use.
Guidance
This skill appears to do what it says (search and book pest-control via Lokuli) and asks for no local credentials, but it will transmit user contact data to an external endpoint. Before installing or invoking: verify lokuli.com is a legitimate service for you; confirm how authentication is handled (the SKILL.md omits API/token requirements); ensure you have user consent before sending names, emails, or phone numbers; ask the integrator where bookings and PII are stored and for a privacy policy; and proceed only if you’re comfortable that the platform’s tools/call mechanism will authenticate to Lokuli securely (TLS) and not leak data to unexpected endpoints.

Review Dimensions

Purpose & Capability
okName/description (book pest-control via Lokuli MCP) match the SKILL.md which defines search, check_availability, and create_booking RPC calls to an MCP endpoint. Nothing requested (no env vars, no binaries) is extraneous to a booking integration.
Instruction Scope
noteInstructions are narrowly scoped to calling Lokuli's MCP via JSON-RPC/SSE for search, availability checks, and booking. However the doc provides sample customer PII (name, email, phone) and does not explain authentication, consent, or what data is returned/stored. The transport line ('SSE | JSON-RPC 2.0 | POST requests') is mildly inconsistent (SSE is event streaming, POST is a request method).
Install Mechanism
okNo install spec and no code files — the skill is instruction-only so nothing will be written to disk or fetched during install.
Credentials
noteThe skill declares no required environment variables or credentials, which is consistent with the package as-is. In practice, calling an external MCP endpoint often requires authentication or API keys; the SKILL.md does not document any credential or auth mechanism, which is a missing justification rather than explicit excess privilege.
Persistence & Privilege
okalways is false and the skill is user-invocable; it does not request persistent installation or elevated platform privileges.