google-maps

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

• Third-party content exposure detected (high risk: 0.80). This skill uses the Membrane CLI to call Google Maps APIs (e.g., search-places, get-place-details, get-place-photo) and thus fetches public Google Maps content—including user-generated reviews and photos—from third-party sources which the agent is expected to read and could materially influence subsequent actions.