azure-data-tables-py
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Data Interaction via External Service: The skill facilitates interaction with Azure Table Storage and Cosmos DB, which are well-known cloud services. It correctly emphasizes the use of
DefaultAzureCredentialto manage authentication securely without hardcoding secrets. - Indirect Prompt Injection Surface: The skill includes functions that ingest data from external NoSQL tables, which represents a potential surface for indirect prompt injection if the retrieved content contains instructions intended for the agent.
- Ingestion points: Data is brought into the agent context through
query_entities,get_entity, andlist_entitiesmethods inSKILL.mdandreferences/non-hero-scenarios.md. - Boundary markers: The skill explicitly recommends the use of parameterized queries (
parametersargument) inquery_entitiesto prevent injection vulnerabilities. - Capability inventory: The skill allows for full CRUD operations (Create, Read, Update, Delete) and batch transactions on Azure Table entities.
- Sanitization: The instructions guide the user to use standard SDK parameterization features to handle external data safely.
Audit Metadata