gws-calendar-agenda
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from an external, potentially untrusted source (Google Calendar events).
- Ingestion points: Data from event titles, descriptions, and locations are brought into the agent's context through the
gws calendar +agendacommand as described inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat calendar content as data rather than instructions.
- Capability inventory: The skill uses the
gwsbinary to perform read-only queries on calendar data. - Sanitization: The instructions do not include steps for sanitizing or escaping the content of calendar events before the agent processes them.
Audit Metadata