Back to skill
Skillv0.1.1
ClawScan security
介绍文案大师（跨境/小红书/公众号等） · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 12, 2026, 6:27 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- An instruction-only Chinese copywriting skill whose declared purpose matches its instructions and which requests no privileges, installs, or credentials.
- Guidance
- This skill is internally consistent and requests no special permissions. Before using, avoid pasting sensitive personal data or secrets into prompts (the skill will process whatever you give it). Also review any persuasive claims the generated copy makes — do not fabricate proof or regulated claims, and ensure outputs comply with platform and advertising rules.
Review Dimensions
- Purpose & Capability
- okThe name/description (Chinese copywriting for platforms like 小红书/公众号/电商/etc.) aligns with the SKILL.md guidance, frameworks, headline/CTA rules, and output modes — nothing requested is unrelated to copywriting.
- Instruction Scope
- okSKILL.md contains detailed authoring rules and templates but does not instruct reading files, accessing environment variables, making network calls, or transmitting data to external endpoints. It stays within the scope of generating/rewriting copy.
- Install Mechanism
- okNo install spec and no code files — this is instruction-only, so nothing will be written to disk or installed.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. There is no disproportionate credential request.
- Persistence & Privilege
- okalways is false and there is no special persistence or cross-skill configuration. Autonomous invocation is allowed by default but is normal for skills and not combined with other concerning privileges.