azure-storage-queue-py
Warn
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION] (MEDIUM): Indirect prompt injection surface via external message ingestion.
- Ingestion points:
queue_client.receive_messages()inSKILL.mdretrieves content from an external Azure Queue. - Boundary markers: Absent. The skill does not provide delimiters or instructions to ignore embedded commands in the message body.
- Capability inventory: The skill can send, update, and delete messages, allowing an attacker to potentially manipulate the queue state if the agent obeys instructions inside a message.
- Sanitization: Absent. Content is processed as raw strings or JSON.
- [EXTERNAL_DOWNLOADS] (INFO): Uses official Microsoft Azure SDKs.
- Evidence:
pip install azure-storage-queue azure-identity. - Trust Status: Downgraded to INFO as Microsoft/Azure is a verified trusted organization.
- [SAFE] (SAFE): Implements secure authentication patterns.
- Evidence: Uses
DefaultAzureCredentialandos.environfor configuration, explicitly flagging hardcoded keys as anti-patterns inreferences/acceptance-criteria.md.
Audit Metadata