azure-eventhub-py
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes official Azure SDK packages, specifically
azure-eventhub,azure-identity, andazure-eventhub-checkpointstoreblob-aio. These are legitimate libraries provided by Microsoft for cloud service interaction. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from an external, potentially untrusted source (Azure Event Hubs).
- Ingestion points: Event bodies are retrieved and printed in
scripts/setup_consumer.pyusing theevent.body_as_str()method. - Boundary markers: The skill does not implement explicit boundary markers or instructions to notify the agent that content from the event hub should be treated as untrusted data.
- Capability inventory: The skill includes network capabilities to communicate with Azure endpoints and read/write event data, but it does not perform arbitrary shell command execution or local file system writes based on the received content.
- Sanitization: No content-based sanitization is applied to the event data; however, the CLI tool in
scripts/setup_consumer.pytruncates event bodies to 200 characters for display purposes.
Audit Metadata