azure-eventgrid-dotnet

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official Microsoft NuGet packages including Azure.Messaging.EventGrid, Azure.Identity, and Microsoft.Azure.Messaging.EventGrid.CloudNativeCloudEvents. These are well-known, trusted dependencies from a recognized vendor.
  • [PROMPT_INJECTION]: The skill facilitates the processing of external event data (CloudEvents and EventGridEvents), which constitutes an indirect prompt injection attack surface.
  • Ingestion points: External data is ingested via EventGridEvent.ParseMany, CloudEvent.ParseMany, and Azure Function triggers as described in SKILL.md.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the provided snippets.
  • Capability inventory: The skill demonstrates capabilities for network publishing via EventGridPublisherClient and logging.
  • Sanitization: The examples show direct deserialization of event data into objects (e.g., egEvent.Data.ToObjectFromJson<MyCustomData>()) without demonstrating sanitization or validation steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:37 PM