azure-blob-storage

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows secure coding practices by avoiding hardcoded credentials and recommending environment variables or Managed Identities for authentication to Azure services.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external files stored in Azure Blob Storage.
  • Ingestion points: SKILL.md (Read CSV/JSON/Parquet from Blob) and connection_examples.md (read_parquet_from_blob).
  • Boundary markers: Absent. The skill reads file contents directly into memory or DataFrames without delimiting or warning the model about untrusted content.
  • Capability inventory: File system write access (downloading blobs to local files), network access to Azure storage endpoints, and data processing via pandas.
  • Sanitization: Absent. The skill performs no validation or sanitization of the data retrieved from blobs before it is used by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:09 AM