extract-webpage-data

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime path calls external scraping/extraction APIs (e.g., v1/proxy/orthogonal/run with url_to_scrape / website_url / url), which fetch outsider-authored webpage text and return it as LLM-readable result.*_content/text that the agent can include in its context.