astrology-backend-integration

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests data from third-party astrology APIs (e.g., AstrologyAPI.com, Prokerala, GeoVedic, AstroSage) — including endpoints like /v1/horo_chart, /v1/planets, dasha and dosha reports — and directly injects those API responses into the AI prompt/kundli context, exposing the agent to untrusted external content that could carry indirect prompt injection.