Back to skill
Skillv1.0.0
ClawScan security
China Plate · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 7:48 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an offline reference skill for parsing Chinese license plates and shows no code execution, credential use, network access, persistence, or account-changing behavior.
- Guidance
- This skill appears safe for its stated offline lookup purpose. Users should still remember that license plates can be personal information and only provide plate numbers when they are comfortable having the assistant process them in the current conversation.
Review Dimensions
- Purpose & Capability
- okThe stated purpose is narrow and coherent: validate and interpret Chinese vehicle plate formats, province abbreviations, city codes, and special plate types.
- Instruction Scope
- okInstructions are limited to using the provided rules and bundled city-code reference when a user asks about a license plate; they do not redirect goals, require tool use, or request hidden actions.
- Install Mechanism
- okThere is no install specification, no required binaries, no dependencies, and no code files.
- Credentials
- okThe only referenced data access is to the bundled references/city-codes.md file, which is proportionate to the plate lookup purpose.
- Persistence & Privilege
- okThe artifacts declare no credentials, environment variables, config paths, persistence, background behavior, or privileged system access.