azure-storage-queue-ts

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Data Ingestion Surface]: The skill facilitates receiving messages from external Azure Storage Queues. Because this data originates from external sources, it represents a potential surface for indirect prompt injection if the content is subsequently processed as instructions by an AI.
  • Ingestion points: External data enters the context via the receiveMessages and peekMessages methods described in SKILL.md.
  • Boundary markers: Code snippets focus on SDK usage and do not explicitly define delimiters for the ingested message content.
  • Capability inventory: The skill enables queue management (creation/deletion) and message lifecycle operations (sending, receiving, and deleting messages) through authorized Azure API calls.
  • Sanitization: The implementation patterns demonstrate the use of JSON.parse() to handle structured message content, which is a recommended practice for validating input schemas.
  • [Credential Configuration]: The skill uses environment variables for sensitive parameters such as AZURE_STORAGE_ACCOUNT_KEY and AZURE_STORAGE_CONNECTION_STRING. This is a standard security practice that avoids hardcoding secrets directly into the skill or application code.
  • [Service Dependencies]: The skill utilizes @azure/storage-queue and @azure/identity. These are official, maintained packages from a well-known vendor intended for secure interaction with Azure cloud services.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-storage-queue-ts