amazon-search

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly states the skill uses the SearchAPI with engine=amazon_search to query Amazon's public catalog and return product information and reviews (user-generated/public content) that the agent is expected to read and use for product recommendations/comparisons, so untrusted third-party content can influence decisions.