azure-storage

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Data Ingestion Surface: The skill provides capabilities to download and process content from external Azure Storage blobs (e.g., via the storage_blob_get command). This represents a potential surface for indirect prompt injection if the stored data contains instructions designed to influence the agent.
  • Ingestion points: Content retrieval from storage blobs using storage_blob_get and az storage blob download.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are explicitly included in the provided snippets.
  • Capability inventory: The skill includes a wide range of capabilities across multiple scripts and CLI commands, including listing, reading, and writing to blobs, file shares, queues, and tables.
  • Sanitization: There is no explicit evidence of content sanitization or validation for retrieved blob data within the skill's instructions.
  • Official SDK Dependencies: The skill identifies and references standard Azure SDK packages for Python, Node.js, Java, Go, and Rust. These dependencies are official Microsoft libraries used for cloud resource management and are standard components for developers working within the Azure ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:06 AM
Security Audit — agent-trust-hub — azure-storage