ai-customer-review-aggregator

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

• Third-party content exposure detected (medium risk: 0.65). Required runtime path allows the operating user to supply materialUrl (public URL) or materialText/materialFile, and the skill’s context composer will ingest that readable content into the LLM; if the URL/text/file contains outsider-authored free text (e.g., scraped web page or third-party comments), it becomes LLM context (indirect prompt injection risk).