Skillv0.1.0

ClawScan security

短视频脚本工坊 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 11, 2026, 2:53 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only Chinese short-video script workflow whose requirements and instructions match its stated purpose and do not request extra credentials, installs, or suspicious actions.
Guidance: This skill appears coherent and low-risk: it only contains instructions and supporting reference documents for generating Chinese short-video script packs. Before using it, avoid uploading sensitive or proprietary videos you don't want shared; review any generated script for legal/compliance issues (false claims, medical claims, platform policy violations) before publishing; and remember the model's outputs may need human editing for factual accuracy and brand fit. Autonomous invocation is allowed by default on the platform (normal), so enable the skill only in agents you trust.

Purpose & Capability: okName, description, and all included reference files (benchmark analysis, formula library, templates, compliance checklist) align with a short-video script creation workflow; there are no unrelated env vars, binaries, or install steps.
Instruction Scope: okSKILL.md limits actions to collecting user inputs (product/topic, 1–5 benchmark videos, audience, goals) and producing script packs using internal reference docs. It does not instruct accessing system files, network endpoints, or secrets beyond user-provided content. Note: it assumes the user will provide benchmark videos or descriptions.
Install Mechanism: okNo install spec and no code files — the skill is instruction-only so nothing is written to disk or downloaded during install.
Credentials: okNo environment variables, credentials, or config paths are requested; the declared requirements are minimal and appropriate for a content-generation workflow.
Persistence & Privilege: okalways is false and there is no indication the skill modifies agent/system settings. disable-model-invocation is default (false), which is normal; this skill does not request elevated persistence.