Amazon Competitor Intelligence Monitor

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly calls APIClaw endpoints (e.g., realtime/product, realtime/reviews, and reviews/analysis) to fetch product descriptions and raw user reviews from third‑party sources and the SKILL.md / scripts/apiclaw.py workflows require the agent to read and act on that untrusted, user‑generated content as part of its analysis and alerting, which could enable indirect prompt injection.