azure-storage-queue-py

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends installing azure-storage-queue and azure-identity via pip. These are official, well-known SDKs provided by Microsoft and are considered safe dependencies.
  • [DATA_EXFILTRATION]: The code snippets include network communication with Azure Queue Storage endpoints (queue.core.windows.net). This is the intended primary purpose of the skill and uses standard, official SDK methods.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides the ability to receive and process messages from external Azure Storage Queues, which constitutes an ingestion point for untrusted data.
  • Ingestion points: Data is brought into the agent's context through queue_client.receive_messages() and queue_client.peek_messages() in SKILL.md.
  • Boundary markers: None; the provided examples do not use delimiters or instructions to treat the message content as untrusted data.
  • Capability inventory: The skill enables full management of queues and message content, including sending, receiving, updating, and deleting messages.
  • Sanitization: There is no evidence of input validation, schema enforcement, or content filtering applied to the retrieved message data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 07:33 PM
Security Audit — agent-trust-hub — azure-storage-queue-py