google-calendar-automation
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading and processing external data from Google Calendar events, which is an untrusted source.
- Ingestion points: Reading calendar events and attendee details as described in the workflow (SKILL.md).
- Boundary markers: No delimiters or specific instructions to treat event content as untrusted data are provided to the agent.
- Capability inventory: The skill outlines capabilities for event creation, modification, deletion, and attendee notification (SKILL.md).
- Sanitization: No instructions are given to sanitize, escape, or validate data retrieved from external calendars before it is processed.
Audit Metadata