calendar-events

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from Salesforce Event fields (Subject, Description, and Location) which are potentially controlled by external parties. This content is ingested via GraphQL and rendered into a UI widget or markdown fallback. This represents a theoretical surface for indirect prompt injection where instructions hidden in calendar events could attempt to influence the agent. However, the risk is negligible as the skill lacks high-risk capabilities like shell execution, file system writes, or arbitrary network access.
  • Ingestion points: Salesforce GraphQL API (Event object fields Subject, Description, and Location).
  • Boundary markers: No specific delimiters are used to wrap the ingested content.
  • Capability inventory: dispatch_readonly (Salesforce API read-only access) and display_widget (UI rendering). No dangerous executive tools are present.
  • Sanitization: No explicit sanitization or escaping of the ingested event content is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 06:39 PM