azure-data-tables-py

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the azure-data-tables and azure-identity packages via pip. These are official libraries provided by Microsoft for Azure service integration and are considered safe.- [PROMPT_INJECTION]: The skill interacts with external data retrieved from Azure Table storage, which presents a surface for indirect prompt injection.
  • Ingestion points: Data is ingested through the query_entities and list_entities methods described in SKILL.md.
  • Boundary markers: The code examples do not use explicit boundary markers for retrieved NoSQL content.
  • Capability inventory: The skill provides full CRUD capabilities, including the ability to create, update, and delete entities and tables as documented in SKILL.md.
  • Sanitization: The documentation explicitly recommends the use of parameterized queries to sanitize input and prevent injection attacks.- [SAFE]: The implementation adheres to security best practices by using DefaultAzureCredential to avoid hardcoded secrets and leveraging managed identity for authentication.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 01:55 AM
Security Audit — agent-trust-hub — azure-data-tables-py