Skillv1.0.0

ClawScan security

Dom Perignon · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 29, 2026, 3:07 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is a read-only, instruction-only informational skill about the Dom Pérignon brand with no installs, no required credentials, and no suspicious instructions — its security surface is minimal.
Guidance: This skill is low risk: it only provides written information about Dom Pérignon and requests no credentials or installs. The main non-security concern is provenance and accuracy — the skill's source/homepage are unknown, so verify facts (dates, figures, pricing) against trusted references before relying on them, and be mindful of copyright if you plan to republish the content.

Purpose & Capability: okThe name/description match the SKILL.md content: an encyclopedic briefing about Dom Pérignon. The skill does not request unrelated resources or credentials.
Instruction Scope: okSKILL.md contains only topical content and a short 'read_when' rubric; it does not instruct the agent to read files, access environment variables, make network calls, or transmit data to external endpoints.
Install Mechanism: okNo install spec is present (instruction-only). Nothing is written to disk and no external packages or downloads are declared.
Credentials: okThe skill requires no environment variables, credentials, or config paths — proportional to an informational brief.
Persistence & Privilege: okalways is false and the skill is user-invocable; autonomous invocation is permitted by default but there are no privileges or actions that raise additional concerns.