caldav-calendars

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external CalDAV calendars which are potentially untrusted ingestion points. If this data contains malicious instructions, the agent might attempt to follow them.
  • Ingestion points: Calendar data retrieved via tools like calendar_occurrences.query and calendar_entities.query (SKILL.md).
  • Boundary markers: The instructions do not explicitly require wrapping external content in delimiters, although they emphasize human confirmation for mutations.
  • Capability inventory: The skill utilizes tools with write and delete permissions, such as events.patch, todos.patch, and calendar_resources.delete (SKILL.md).
  • Sanitization: No specific sanitization or escaping of external calendar content is mandated before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 03:07 AM