azure-storage-queue-py

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to ingest data from external Azure Storage Queues. As this data originates from outside the immediate environment, it should be treated as untrusted.
  • Ingestion points: Data enters the agent's context through the receive_messages() and peek_messages() methods in SKILL.md and references/non-hero-scenarios.md.
  • Boundary markers: The provided code snippets do not include specific delimiters or instructions for the agent to ignore embedded commands within message content.
  • Capability inventory: The skill enables network operations via the Azure SDK and outputting message content to the console/logs.
  • Sanitization: The examples demonstrate direct printing and processing of message content without explicit sanitization or validation steps.
  • Authentication Best Practices: The skill correctly emphasizes the use of DefaultAzureCredential and managed identities over hardcoded connection strings or access keys, which aligns with secure infrastructure standards.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-storage-queue-py