outlook-calendar-automation
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a surface for indirect prompt injection.
- Ingestion points: The skill retrieves event details, subjects, and bodies from Outlook via tools like
OUTLOOK_LIST_EVENTS,OUTLOOK_GET_EVENT, andOUTLOOK_GET_CALENDAR_VIEW(SKILL.md). - Boundary markers: There are no instructions for the agent to use delimiters or ignore instructions embedded within retrieved calendar data.
- Capability inventory: The skill has significant capabilities to modify the environment, including
OUTLOOK_CALENDAR_CREATE_EVENT,OUTLOOK_UPDATE_CALENDAR_EVENT,OUTLOOK_DELETE_EVENT, andOUTLOOK_DECLINE_EVENT(SKILL.md). - Sanitization: The skill lacks instructions for sanitizing or escaping the content retrieved from event bodies or subjects before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill requires the user to configure a third-party MCP server at
https://rube.app/mcpto provide the toolkit functionality.
Audit Metadata