lumi-app-finder

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

• Third-party content exposure detected (high risk: 0.75). The required workflow reads the outsider-provided JSON catalog text at runtime (e.g., references/<locale>.json, which contains free-form localized strings like publisher_query, source_persona_query, and decision_context) and then uses it to generate the recommendation; this is outsider-authored content ingestion from prebuilt catalog files rather than user/organization-authored text.