keyapi-amazon-ecommerce

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls the KeyAPI MCP endpoint (https://mcp.keyapi.ai/amazon/mcp) and SKILL.md lists nodes like product_reviews, product_review_details, influencer_posts and influencer_post_products that fetch Amazon user-generated content which the agent ingests and uses to synthesize reports and drive analysis, so untrusted third-party content can materially influence behavior.