Back to skill
Skillv1.0.0
ClawScan security
Content Structure Designer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 6, 2026, 10:02 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only content-outline/template helper and its requests and instructions are proportionate to that purpose.
- Guidance
- This skill is coherent and low-risk: it only supplies writing templates and checklists, asks for no credentials, and has no install code. Before installing, verify you trust the skill source (owner ID unknown) if that matters to you. Avoid pasting sensitive or private documents into the skill when asking for tailored outlines, and spot-check any factual or data-driven suggestions the skill produces (the templates may recommend including numbers or case studies that you should verify).
Review Dimensions
- Purpose & Capability
- okName/description (内容结构设计) match the SKILL.md: the skill only provides templates, workflow steps, and checklists for designing content structure. It does not request unrelated resources (no env vars, binaries, or config paths).
- Instruction Scope
- okSKILL.md contains triggers/keyword hints and many structured templates and guidance. It does not instruct the agent to read local files, access environment variables, call external endpoints, or exfiltrate data. Scope is narrowly focused on drafting/optimizing content structure.
- Install Mechanism
- okNo install spec and no code files — instruction-only. Nothing is written to disk or downloaded during install.
- Credentials
- okNo credentials, environment variables, or config paths are required. Requested privileges are minimal and appropriate for a templates-only skill.
- Persistence & Privilege
- okSkill is not marked always:true and uses default autonomous-invocation behavior. It does not request persistent system changes or modify other skills' config.