azure-storage

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and provides installation instructions for official Microsoft Azure SDKs across multiple languages (Python, JavaScript, Java, Rust, Go). These dependencies are hosted on well-known, official package registries.
  • [PROMPT_INJECTION]: The skill enables the agent to read content from external Azure Storage blobs, which creates a surface for indirect prompt injection if the retrieved data contains malicious instructions intended to influence the agent's behavior.
  • Ingestion points: The "storage_blob_get" tool and "az storage blob download" CLI commands in "SKILL.md" allow the agent to ingest external data.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat blob content as untrusted data.
  • Capability inventory: The skill includes capabilities for listing accounts/containers, downloading blobs, and uploading content ("storage_blob_put").
  • Sanitization: There are no instructions for sanitizing or validating the content retrieved from external storage before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 05:50 PM
Security Audit — agent-trust-hub — azure-storage