Back to skill
Skillv1.0.0
ClawScan security
直播带货话术生成器 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 2:31 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only generator for live-stream sales scripts and its declared requirements and instructions are consistent with that purpose.
- Guidance
- This skill appears coherent and low technical risk because it only contains generation instructions and asks for no credentials or installs. Before installing, consider: (1) review generated scripts for accuracy and compliance with advertising/consumer protection rules on your platform (avoid false claims or unlawful pressure tactics); (2) verify outputs do not include sensitive or personal data when you provide inputs; (3) test the skill with non-production prompts first to ensure tone and claims are appropriate. Because it is instruction-only, the main risk is content quality and policy compliance rather than technical exploitation.
Review Dimensions
- Purpose & Capability
- okName and description match the SKILL.md content. The skill requires no binaries, env vars, or installs — which is proportionate for a text-generation helper.
- Instruction Scope
- okSKILL.md only describes the types of scripts to generate (openings, product intros,促单, interaction, closing) and the intended formats. It does not instruct the agent to read unrelated files, use credentials, or send data to external endpoints.
- Install Mechanism
- okNo install spec or code files are present (instruction-only), so there is nothing written to disk or executed at install time.
- Credentials
- okNo environment variables, credentials, or config paths are requested — proportional to a content-generation skill.
- Persistence & Privilege
- okalways is false and there is no indication the skill persists state or modifies other skills or system settings.