amazon-keyword-research

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

• Third-party content exposure detected (high risk: 1.00). The skill clearly fetches and parses live public third‑party content—scripts/research.sh calls Amazon's autocomplete API (https://completion.{DOMAIN}/...), SKILL.md requires using web_search on amazon.com and web_fetch on Google Trends—then interprets that data to score and recommend products, so untrusted user-generated/search content could influence agent actions and enable indirect prompt injection.