gws-calendar

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the gws command-line tool to perform operations on Google Calendar resources. This is the primary intended function of the skill.
  • [PROMPT_INJECTION]: The skill provides an interface to read external data from Google Calendar, which creates a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent context through methods such as events.get, events.list, and calendarList.list which fetch event descriptions and metadata.
  • Boundary markers: The instructions do not specify any delimiters or boundary markers to isolate retrieved calendar data from agent instructions.
  • Capability inventory: The skill allows for management of events and access control lists (ACLs), including creation, modification, and deletion.
  • Sanitization: No explicit sanitization or validation of the retrieved calendar content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 08:50 AM
Security Audit — agent-trust-hub — gws-calendar