azure-eventhub-py

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs official Microsoft Azure SDK packages (azure-eventhub, azure-identity, azure-eventhub-checkpointstoreblob-aio) from public registries to enable cloud service interactions.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and processing data from an external source (Azure Event Hubs).
  • Ingestion points: The on_event function in SKILL.md processes untrusted event data via the event.body_as_str() method.
  • Boundary markers: The provided examples do not use delimiters or explicit instructions to prevent the agent from interpreting instructions contained within the event body.
  • Capability inventory: The skill includes capabilities for both network ingestion (EventHubConsumerClient) and data transmission (EventHubProducerClient) as documented in SKILL.md.
  • Sanitization: No validation or sanitization logic is implemented in the provided code snippets to filter potentially malicious content from the event stream.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 08:23 PM