amazon-market-entry-analyzer

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

• Third-party content exposure detected (medium risk: 0.30). The Amazon Market Entry Analyzer’s runtime workflow ingests outsider-authored free text via ZooData-provided customer reviews when it falls back to the “review fallback toolkit” (reviews-raw → review-tag-prompt renders prompts with each raw review JSON → caller LLM tags → reduce/aggregate), meaning attacker-controlled review text can reach the LLM at runtime.