product-hunt-scraper

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill searches Product Hunt launches (public web content) and then enriches top launches by fetching/processing their text (e.g., launch pages/taglines/company info), which is outsider-authored free text ingested into the agent’s LLM context via the startup-launches /launches and company-intel /intelligence steps.