shiny-notifications

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists exclusively of documentation and usage instructions for a legitimate third-party library. All referenced components and namespaces are consistent with the Shiny framework's official ecosystem.
  • [EXTERNAL_DOWNLOADS]: The skill references the Shiny.Notifications NuGet package and its dependencies (Shiny.Core, Shiny.Locations, Shiny.Support.Repositories), which are standard resources for .NET development.
  • [PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface where user-provided text from notification replies is processed by the application.
  • Ingestion points: MyNotificationDelegate.OnEntry in SKILL.md and reference/api-reference.md receives data from NotificationResponse.Text.
  • Boundary markers: No delimiters or boundary markers are demonstrated in the provided usage examples.
  • Capability inventory: INotificationManager (defined in reference/api-reference.md) provides capabilities to send, cancel, and manage notifications, which are then influenced by the received responses.
  • Sanitization: No explicit sanitization or validation of the input text is shown in the provided code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:56 PM
Security Audit — agent-trust-hub — shiny-notifications