google-calendar
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Category 8: Indirect Prompt Injection (LOW): The skill processes user-provided data such as event titles and descriptions. While it lacks explicit boundary markers or sanitization logic to prevent the agent from being influenced by malicious content within those fields, this is a common surface for data-driven skills and is handled by the platform's underlying safety layers.
- Ingestion points: Input JSON fields in
SKILL.md(e.g.,event_title,event_description). - Boundary markers: Not present.
- Capability inventory: Executes workflows via
refly skill run. - Sanitization: Not present.
- Command Execution (SAFE): The skill uses
reflyCLI commands for workflow management andjqfor JSON processing, which are expected behaviors for this platform's skills.
Audit Metadata