cheerio-parsing

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can fetch arbitrary public HTML via axios.get(url) and then parses it with cheerio.load(response.data), so any free text contained in outsider-authored web pages becomes LLM-readable content through the extracted .text()/.html() fields.