Back to skill
Skillv1.0.0
ClawScan security
Writing Polish · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 12, 2026, 3:29 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- An instruction-only Chinese writing/rhetoric polishing skill whose declared purpose matches its instructions and that requests no extra privileges or installs.
- Guidance
- This skill is internally consistent and low-risk: it only contains editing rules and asks for no credentials or installs. Before pasting sensitive material, remember any text you provide will be visible to the model doing the edits; avoid sending secrets or personally identifying information. Also check how the platform renders deletion/compare formatting (some channels strip strikethrough or diffs), and verify significant structural edits with the author rather than accepting them automatically.
Review Dimensions
- Purpose & Capability
- okName, description, and the SKILL.md consistently describe a Chinese writing and polishing assistant. The skill requires no binaries, env vars, or installs—everything in the manifest is appropriate for a text-editing helper.
- Instruction Scope
- okSKILL.md contains detailed, narrowly scoped authoring rules and a concrete four-step workflow for reading, diagnosing, editing, and returning text. It does not instruct reading system files, environment variables, or sending data to any external endpoint beyond normal model responses.
- Install Mechanism
- okThere is no install spec and no code files; this is instruction-only. That is the lowest-risk install profile and matches the skill's purpose.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. Nothing requested appears disproportionate to a writing/polish assistant.
- Persistence & Privilege
- okalways is false and the skill does not request elevated/persistent platform privileges or modifications to other skills. The default ability for the agent to invoke the skill autonomously is unchanged (normal platform behavior).