Amazon Market Entry Analyzer — GO/CAUTION/AVOID Verdicts

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

• Third-party content exposure detected (high risk: 0.90). The skill's CLI and composite workflows (e.g., scripts/apiclaw.py cmd_market_entry, cmd_report, and review fallbacks) call APIClaw endpoints such as realtime/product, realtime/reviews, products/search and reviews/analysis to fetch public Amazon product pages and user-generated reviews, and the agent is instructed to read/interpret those results (including using the LLM to tag/aggregate raw reviews) to produce GO/CAUTION/AVOID decisions—exposing it to untrusted third-party content that can materially influence actions.