zendesk

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly connects to Zendesk via Membrane and calls actions like "list-ticket-comments", "list-tickets", and "search" to fetch user-generated ticket/comments from a third-party support system (Zendesk), which the agent is expected to read and which could materially influence subsequent actions.