Enterprise Integration Skill

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches and displays user-generated content from Microsoft Graph (see graphFetch calling https://graph.microsoft.com/v1.0 and the handleCalendarCommand/getCalendarEvents flow in SKILL.md), so third-party data (emails/calendar events/people) are ingested and streamed into the agent workflow and could influence subsequent actions.