amazon-analyse

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public third‑party data (including user-generated Amazon reviews and other marketplace data) from the Sorftime MCP service (see SKILL.md and references/api-tools-reference.md calling product_reviews, product_traffic_terms, competitor_product_keywords, etc.), and those results are read and used by the agent to drive analysis and recommendations, creating a clear vector for indirect prompt injection.