wechat-to-shopify-blog

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses arbitrary public WeChat article URLs (mp.weixin.qq.com) via scripts/fetch-wechat-article.mjs (and also fetches public storefront homepage meta in scripts/shopify-context.mjs), and the parsed article text/images are directly used to drive rewriting, product selection, image uploads, and Shopify draft creation—so untrusted third-party content is read and can materially influence tool use and actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The bundled script fetch-wechat-article.mjs performs a runtime fetch of user-supplied WeChat article URLs (e.g., https://mp.weixin.qq.com/...), parses the article body and images, and injects that content into the agent's processing/context used to drive prompts and output, so the external mp.weixin.qq.com content directly controls the agent's instructions.