data-scraper-agent

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 sources via the scraper step (e.g., requests/BeautifulSoup/RSS/Playwright fetches arbitrary public pages/APIs, then _build_prompt() embeds the scraped item JSON into the Gemini prompt), which is then sent to the LLM for enrichment.