Calendar Planner
Warn
Audited by Snyk on Apr 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly reads calendar data from external providers (see "External Endpoints" in SKILL.md listing https://www.googleapis.com/calendar/v3/* and https://graph.microsoft.com/v1.0/* and the CLI recipes in commands.md), and its runtime workflow and scripts (calendar_merge.py, calendar_guard.py, week_plan.py) parse event titles/notes/tags and use them to make planning and execution decisions, so untrusted/user-generated calendar content could materially influence agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata