aws-wechat-article-publish

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

• Third-party content exposure detected (high risk: 0.80). The skill's runtime scripts (scripts/getdraft.py and scripts/publish.py) explicitly call the public WeChat API (api.weixin.qq.com) to fetch drafts and published articles (e.g., freepublish/batchget, draft/get, freepublish/getarticle) and the SKILL.md and references describe using these fetched, user-generated article contents to auto-fill related-links and to make publish decisions (e.g., tempkey checks), so untrusted third-party content is ingested and can influence agent actions.