Back to skill
Skillv1.0.0
ClawScan security
chinese-sentence-correction · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 7:42 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only Chinese sentence correction skill with no code, installs, credentials, or external access.
- Guidance
- This skill appears safe for its stated purpose. Before installing, users should simply confirm they want an instruction set that returns only the corrected Chinese sentence without explanation.
Review Dimensions
- Purpose & Capability
- okThe artifacts consistently describe a narrow writing task: correcting Chinese ill-formed sentences with minimal edits while preserving meaning.
- Instruction Scope
- okThe instructions are limited to reading, diagnosing, minimally editing, and checking a sentence; they do not request tool use, system changes, or authority beyond text transformation.
- Install Mechanism
- okNo install spec, binaries, dependencies, or code files are present; the skill is instruction-only.
- Credentials
- okNo environment variables, credentials, files, network access, or local system access are requested.
- Persistence & Privilege
- okThe artifacts show no persistence, background behavior, privilege requests, memory use, or account access.