wechat copywriter pro
PassAudited by ClawScan on May 15, 2026.
Overview
This skill is mostly coherent for generating WeChat article drafts, but it runs a local Python fetch script that sends your keywords to an external service, so avoid sensitive topics or private writing samples.
This skill appears safe to use for ordinary public-topic copywriting. Before installing or invoking it, be comfortable with running its Python script and with your search keywords being sent to its external trend-data service. Avoid providing confidential business ideas, private diary text, client names, or sensitive personal details, and review any generated article before publishing.
Findings (5)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Using the skill may cause your agent to run the included Python script as part of normal article generation.
The workflow directs the agent to run a local Python script using user-derived keywords. This is central to the skill's purpose and scoped to data fetching, but it is still local command execution.
python scripts/fetch_gzh_trends.py --keyword "<提炼出的关键词>" --max-items 10 --output-format markdown
Only use it in an environment where running this script is acceptable, and ensure keywords are passed as arguments rather than manually concatenated into unsafe shell commands.
A future compatible version of the dependency could be installed depending on the local environment.
The skill declares an unpinned Python package dependency. Requests is a common and purpose-aligned dependency here, but the version range is not locked.
dependency:\n python:\n - requests>=2.28.0
For stronger reproducibility, the publisher should pin or lock dependencies; users should install dependencies from trusted package indexes.
Your requested topic or keyword may be shared with the external trend-data provider.
The script sends the user-derived keyword to an external API endpoint. This matches the trend-fetching purpose, but the external data boundary is not prominently declared in the registry metadata.
base_url = "https://onetotenvip.com/skill/cozeSkill/getWxCozeSkillData" ... params = {"keyword": keyword, "source": "公众号爆款写文案-ClawHub"}Do not use confidential campaign plans, private client names, or sensitive personal topics as keywords unless you are comfortable sending them to that provider.
Private notes, diary entries, or unpublished drafts could be included in the model context if you provide them.
The skill invites optional personal writing samples for style matching. The artifacts do not show storage or reuse beyond the current generation, but the samples may contain private information.
可以发几段你平时的文字给我，我会学习并融入生成的文案中
Share only sanitized writing samples and remove names, private events, client details, or anything you would not want processed for this task.
Users might over-trust generated public content and publish without sufficient legal, brand, or platform-policy review.
The skill describes generated copy as compliance-checked and directly publishable. The artifacts mainly show prompt-level writing rules, not an independent compliance checker.
输出的文案已按照公众号社区规范校验...复制即可使用。建议发布前再通读一遍做微调。
Treat the output as a draft and review it for accuracy, originality, copyright, brand fit, and WeChat policy compliance before publishing.