meeting-scheduler
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill implements mitigations for indirect prompt injection risks inherent in processing calendar data.
- Ingestion points: Meeting metadata and descriptions are ingested via calendar listing tools described in "SKILL.md".
- Boundary markers: Clear instructional constraints are provided to ensure the agent ignores any commands embedded within event content.
- Capability inventory: The agent can manage events using the authenticated Google and Microsoft 365 toolsets.
- Sanitization: Security rules require flagging suspicious content and prohibit the execution of instructions found in external event notes.
Audit Metadata