bilingual-content

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests outsider-authored free text from public web content: scripts/scrape_medium_article.py fetches a Medium URL at runtime, extracts article DOM text (paragraphs/headers/code captions) into article_data.json, and scripts/generate_bilingual_md.py reads that JSON and inserts the extracted text into the LLM context/output (via the agent’s subsequent translation step).