google-calendar-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation encourages placing 'agent prompts' within the description field of calendar events, creating a vector for indirect prompt injection where instructions embedded in data could influence agent behavior.
- Ingestion points: The skill utilizes tools such as
list_eventsandget_eventto ingest event summaries and descriptions as described inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for processing these event fields.
- Capability inventory: The skill provides the ability to create, update, and delete events via
CallDynamicTool, which could be abused if the agent follows instructions found in a calendar description. - Sanitization: There is no mention of sanitizing or validating the content of the event descriptions before processing the embedded prompts.
- [EXTERNAL_DOWNLOADS]: The skill references an external third-party repository at
https://skills.sh/odyssey4me/agent-skills/google-calendaras an alternative implementation.
Audit Metadata