gws-calendar

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external Google Calendar events.
  • Ingestion points: Event metadata, titles, and descriptions fetched from connected Google accounts as described in SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters or guidance for the agent to ignore instructions embedded in event data.
  • Capability inventory: The google_calendar tool provides capabilities for creating, updating, and deleting events across all connected accounts.
  • Sanitization: There is no mention of sanitizing or validating the content of calendar events before processing.
  • [NO_CODE]: The skill consists entirely of instructional markdown and does not include any executable scripts, binaries, or configuration files that execute code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 02:59 AM