google-play

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

• Third-party content exposure detected (high risk: 1.00). This skill exposes the agent to untrusted third-party content because SKILL.md includes endpoints (e.g., GET /google-play/.../reviews and GET /google-play/.../reviews/{reviewId} via https://gateway.maton.ai/google-play/...) that fetch public Google Play user reviews (user-generated content) which the agent is expected to read and can directly influence actions like composing replies.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill exposes the Google Play (Android Publisher) API via a managed gateway and includes explicit monetization endpoints: creating/updating in‑app products and subscriptions, purchase endpoints, canceling subscriptions, and a refund endpoint (POST .../purchases/subscriptions/{subscriptionId}/tokens/{token}:refund). Those endpoints perform payment-related actions (including issuing refunds and managing subscriptions), so this skill provides direct financial execution capability rather than a generic tool.