syncfusion-vue-scheduler

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a data ingestion surface where untrusted content from external sources (Web APIs, OData services, Google Calendar) can be loaded into the scheduler and subsequently processed by an AI agent through the integrated WebMCP tools.
  • Ingestion points: Remote data is fetched via DataManager adaptors as documented in references/data-binding.md and references/advanced-features.md.
  • Boundary markers: The documentation and examples do not provide or recommend the use of delimiters or instructions to ignore potential commands embedded in event subjects or descriptions.
  • Capability inventory: The WebMcpScheduler module enables the agent to perform actions such as createEvent, updateEvent, deleteEvent, changeView, and navigateDate as described in references/webmcp-integration.md.
  • Sanitization: There is no mention of sanitizing or validating the natural language content of events to prevent them from potentially influencing the agent's behavior during interaction with the scheduler.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 06:12 AM