Back to skill
Skillv1.0.0
ClawScan security
Chinese Baby Names · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 28, 2026, 7:50 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is instruction-only and its requested inputs and behavior match its stated purpose of generating Chinese baby names; it asks for no credentials, installs, or system access.
- Guidance
- This skill appears coherent and low-risk: it only needs user-provided naming preferences to produce suggestions and asks for no secrets or installs. Before using, avoid entering highly sensitive personal data (ID numbers, full family histories) into any skill. If you want extra assurance, test with non-identifying example inputs first and verify culturally or legally important names (e.g., check character compatibility with local ID/hukou systems or consult native speakers).
Review Dimensions
- Purpose & Capability
- okName, description, and SKILL.md all consistently describe generating Chinese baby-name suggestions; no unrelated permissions, binaries, or external services are requested.
- Instruction Scope
- okRuntime instructions only ask the agent to collect user-provided naming preferences (surname, gender, style, meaning, taboo characters, etc.) and generate suggestions in a defined output format. They do not instruct reading files, accessing env vars, or sending data to external endpoints.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill, so nothing will be written to disk or installed.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths; the information it asks from users (name preferences) is appropriate for the purpose.
- Persistence & Privilege
- okalways:false and default autonomous invocation are used. The skill does not request elevated or persistent system privileges or modify other skills/configuration.