scrape-leads

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

• Third-party content exposure detected (high risk: 0.90). The skill's scrape_apify.py uses Apify to collect public website/listing data into .tmp/leads.json (scraped open web), and that JSON (including company_description/keywords) is fed into scripts/classify_leads_llm.py which inserts the untrusted scraped text into LLM prompts and uses the LLM's classifications to filter/save leads, so third-party content can directly influence decisions and tool actions.