review-analyzer

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text is ingested into the LLM via analyze_reviews/voc_full: the tool embeds reviews[:150] (including body/content from Shulex VOC API or user-provided CSV/URL) into the user_content JSON block sent to Claude (mcp_server/clients/analyzer.py), and those review bodies are authored by non-operating users (Amazon reviewers / CSV authors).