skills/microsoft/skills/azure-storage/Gen Agent Trust Hub

azure-storage

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Technical Documentation and Reference Content: The skill serves as a reference guide for Azure Storage services, providing CLI commands and SDK code snippets for Python, TypeScript, Java, Rust, and Go. These resources facilitate standard interaction with Azure cloud services using official tooling.
  • Authentication Security Best Practices: A dedicated section provides guidance on secure Azure authentication, explicitly recommending Managed Identities and Azure Role-Based Access Control (RBAC) for production environments to mitigate risks associated with hardcoded credentials and secret management.
  • Security Consideration: Data Interaction Surface: The skill references tools like storage_blob_get and az storage blob download which allow for the retrieval of external content. As with any system that ingests external data, there is a potential consideration for indirect prompt injection if the content being processed contains instructions meant to influence the agent.
  • Ingestion points: Access via storage_blob_get and az storage blob download (SKILL.md).
  • Boundary markers: No specific delimiters or safety instructions are defined in the reference materials for handling retrieved content.
  • Capability inventory: The documentation covers both read operations and write operations (e.g., storage_blob_put) across multiple storage services.
  • Sanitization: No explicit content sanitization or validation routines are included in the provided SDK or CLI examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:52 PM
Security Audit — agent-trust-hub — azure-storage