why

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow actively queries multiple MCP-backed systems (issue/ticket trackers, long-form docs, real-time chat, observability, error tracking, analytics) based on the target and question, and those sources can contain outsider-authored free text (e.g., issue comments, ticket descriptions, chat messages, incident notes) that the investigators then read and quote.