amazon-pricing-command-center

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via ZooData API JSON fields that include user-generated product content (e.g., realtime/product title/description/features, and reviews/analysis-derived consumerInsights/review text), which the agent then uses to produce the final report; this is runtime-fetched, non-user-authored content.