微信公众号文章解析器
Analysis
The skill appears purpose-aligned for fetching and summarizing WeChat articles, with minor cautions around loose URL validation and manual dependency installation.
Findings (2)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
if (!url.includes('mp.weixin.qq.com')) { ... }
...
await page.goto(url, { waitUntil: 'domcontentloaded', timeout: 30000 });The script launches a browser against a user-supplied URL after only checking whether the string contains the WeChat domain, so a crafted non-WeChat URL containing that substring could still be opened.
npm install playwright cheerio # 安装浏览器(仅需一次) npx playwright install chromium
The documented setup installs external npm packages and downloads a Playwright browser. This is expected for browser-based scraping, but it is not represented by an install spec and should be treated as an external dependency step.
