microsoft-outlook

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context when the runtime uses Apideck’s CRM/Proxy calls to fetch Microsoft Outlook content (e.g., emails/messages or other user-provided Outlook body text) and the agent then summarizes/uses that retrieved text in its LLM prompt.