Back to skill
Skillv1.0.0
ClawScan security
Martell · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 3:06 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This skill is a read‑only, instruction-only informational doc about Martell cognac; it requests no credentials, installs, or actions beyond presenting content and is internally consistent with its description.
- Guidance
- This skill is purely informational and appears safe: it only provides a Chinese-language writeup about Martell and requires no credentials or installs. You can install and use it without exposing secrets. As a general precaution, prefer skills with a known source or homepage when you need trusted provenance, but for casual research this skill poses no apparent risk.
Review Dimensions
- Purpose & Capability
- okName/description (Martell cognac history/market analysis) match the SKILL.md content. The skill requests no binaries, env vars, or config paths — appropriate for a documentation-style skill.
- Instruction Scope
- okSKILL.md is static content and does not instruct the agent to read system files, access environment variables, call external endpoints, or perform actions outside presenting research/analysis prompts.
- Install Mechanism
- okNo install spec and no code files are present; nothing will be written to disk or fetched during install — lowest-risk model for a skill.
- Credentials
- okNo environment variables, credentials, or config paths are required. There is nothing disproportionate to the stated informational purpose.
- Persistence & Privilege
- okalways is false and the skill does not request elevated or persistent privileges; autonomous invocation is allowed by platform default but presents no added risk given the skill's read-only nature.