outlook-calendar-automation
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from external calendar events without defined boundaries or sanitization.
- Ingestion points: External data enters the agent context via
OUTLOOK_LIST_EVENTS,OUTLOOK_GET_EVENT, andOUTLOOK_GET_CALENDAR_VIEWas described inSKILL.md. - Boundary markers: There are no instructions to use delimiters or ignore potential commands embedded within event subjects or bodies.
- Capability inventory: The skill allows the agent to create (
OUTLOOK_CALENDAR_CREATE_EVENT), update (OUTLOOK_UPDATE_CALENDAR_EVENT), and delete (OUTLOOK_DELETE_EVENT) calendar records, as well as manage invitations. - Sanitization: No validation or filtering of event content is specified before processing.
Audit Metadata