pricing-strategy

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s required workflow accepts user-supplied materialUrl/materialFile/materialText and (per the form schema) uses them in a context composer; if materialUrl points to public web content or materialFile/materialText contains outsider-authored text, that free text is ingested into the LLM context, enabling indirect prompt injection.