Back to skill
Skillv1.0.0
ClawScan security
language-polisher · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 10, 2026, 6:01 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only text-polishing helper with no installs, no required credentials, and instructions that match its stated purpose.
- Guidance
- This skill appears coherent and low-risk, but remember it will process whatever text you give it — avoid submitting secrets or sensitive personal data. The SKILL.md asks the agent to explain why edits were made, so explanations may restate or summarize input; if you don't want that, instruct the agent not to include explanations. Because the skill is instruction-only and requests no credentials, the main concern is privacy of the text you provide rather than hidden functionality.
Review Dimensions
- Purpose & Capability
- okName and description (polishing, grammar, rewriting) align with the SKILL.md instructions. The skill declares no binaries, env vars, or config paths — all consistent with a lightweight text-editing helper.
- Instruction Scope
- noteSKILL.md stays focused on rewriting text, preserving meaning, and producing 1–2 alternatives. It also asks to 'Explain why you made such changes' which is reasonable for a polisher but will produce additional explanatory text (may restate or summarize user content). The instructions do not request reading files, env vars, or sending data to other endpoints.
- Install Mechanism
- okNo install spec and no code files — this is instruction-only, so nothing is written to disk or downloaded during install.
- Credentials
- okNo environment variables, credentials, or config paths are required; requested capabilities are minimal and proportional to a text-polishing task.
- Persistence & Privilege
- okalways is false and the skill does not request persistent or system-wide changes. It does not modify other skills or global agent settings.