etermin

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md explicitly instructs the agent to call the external ETermin API via Membrane (e.g., "membrane action run", "membrane request" and the "List Ratings" action), which can return untrusted, user-generated content (reviews, appointment notes, contacts) that the agent will read and that could materially influence subsequent actions.