google-calendar-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Google Calendar events (such as summaries, descriptions, and attendee lists) which can be controlled by third parties. This creates a surface for indirect prompt injection if an attacker invites the user to an event containing malicious instructions designed to hijack the agent's behavior during automation workflows.
- Ingestion points: Data is ingested via
GOOGLECALENDAR_FIND_EVENTandGOOGLECALENDAR_EVENTS_LIST(SKILL.md). - Boundary markers: No explicit boundary markers or instructions to treat event content as untrusted data are provided.
- Capability inventory: The skill provides significant write capabilities, including
GOOGLECALENDAR_CREATE_EVENT,GOOGLECALENDAR_PATCH_EVENT, andGOOGLECALENDAR_DELETE_EVENT, which could be abused if an injection is successful. - Sanitization: The instructions do not include steps for sanitizing or validating the content of calendar fields before the agent acts upon them.
Audit Metadata