microsoft-outlook

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly reads and proxies Microsoft Outlook mailbox content (see SKILL.md sections listing "Email", "Attachment", "Mailbox" and the "membrane request CONNECTION_ID /path/to/endpoint" proxy), which ingests user-generated emails/attachments from external senders that the agent will read and that could contain instructions influencing actions.