article-extractor

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow reads outsider-authored free text directly from user-provided “ARTICLE_URL” by fetching the URL contents and extracting article text via reader, trafilatura, or the fallback method (curl -s "$ARTICLE_URL" piped into HTML parsing), so an outsider can supply poison HTML/page content for ingestion.