outlook-calendar-automation
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the processing of calendar event data.
- Ingestion points: Data enters the agent's context through
OUTLOOK_LIST_EVENTS,OUTLOOK_GET_EVENT, andOUTLOOK_GET_CALENDAR_VIEWtools defined in SKILL.md. - Boundary markers: The skill instructions do not specify any delimiters or safety prompts to prevent the agent from obeying instructions hidden within event subjects or bodies.
- Capability inventory: The agent has the ability to create, update, and delete events, and manage attendee lists, which could be exploited if malicious instructions are processed.
- Sanitization: No sanitization or content validation steps are documented for the external data retrieved from Outlook.
- [DATA_EXFILTRATION]: The skill directs users to connect to an external MCP server at
https://rube.app/mcp. - This network operation is the primary mechanism for the skill's functionality and is documented as a prerequisite for using the Outlook toolkit.
Audit Metadata