wechat-article-fetcher

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's scripts and SKILL.md show it fetches and parses arbitrary public WeChat article URLs (https://mp.weixin.qq.com/s/...) via axios/cheerio in scripts/fetch.js, ingesting untrusted user-generated webpage content and converting it into Markdown/front-matter that the tool will read and produce outputs from, so third-party page content can influence the agent's outputs and downstream behavior.