kunze-ad-setup

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls research_products(keyword=...) in Phase 1 to collect competitor ASINs from Amazon and delegates amazon_keyword_research(asins=[...]) in Phase 2 (via sub-agents) to fetch keyword/search-volume data for those public ASINs—untrusted third-party marketplace and keyword data that the agent reads and uses to drive campaign-building decisions.