google-calendar-automation
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute local Python scripts (
scripts/auth.pyandscripts/gcal.py) to perform authentication and interact with the Google Calendar API. - [NO_CODE]: The core implementation scripts referenced in the instructions are missing from the skill package (only metadata and documentation are provided), indicating this skill is a set of instructions for a toolset that must be pre-installed in the user's environment.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it retrieves and processes untrusted data from Google Calendar event fields like descriptions and locations.
- Ingestion points: Untrusted data enters the agent context via
list-eventsandget-eventoperations. - Boundary markers: No delimiters or specific safety instructions are provided to help the agent distinguish between data and commands within event fields.
- Capability inventory: The agent has permissions to create, update, and delete calendar events, and manage invitations based on the results of its actions.
- Sanitization: There is no evidence of validation or sanitization of the retrieved event content before it is processed by the agent.
Audit Metadata