Back to skill
Skillv1.0.0
ClawScan security
Korean · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 5:32 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only Korean writing style skill with no code, install steps, credentials, or data access; the main thing to notice is that it favors casual and sometimes slangy wording.
- Guidance
- This skill appears safe from an agentic security perspective. Before using it, remember that it defaults toward casual Korean and includes slang or crude intensifiers, so specify polite, formal, workplace, or family-safe wording when needed.
Review Dimensions
- Purpose & Capability
- okThe artifact is coherent with its stated purpose: it gives guidance for making Korean writing sound more natural and casual.
- Instruction Scope
- okThe instructions are limited to writing style, register, contractions, particles, slang, and tone; they do not direct tool use, account access, persistence, or unrelated actions.
- Install Mechanism
- okThere is no install spec, no code, no required binaries, and no required environment variables.
- Credentials
- okThe skill requests no filesystem, network, credential, or device access, which is proportionate for a language-style helper.
- Persistence & Privilege
- okThe artifacts show no persistence mechanism, background activity, privilege escalation, or use of local profiles or credentials.