ai-amazon-search-optimization

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

• Third-party content exposure detected (medium risk: 0.65). Skill runtime ingests user-supplied free text/links via materialText/materialUrl/materialFile in the context composer; if materialUrl points to public web content or materialText/files contain outsider-authored text, that text can be fed into the LLM (indirect prompt injection risk).