azure-cosmos-py

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • Secure Authentication Guidance: The skill emphasizes the use of DefaultAzureCredential for authentication. This approach is a security best practice as it avoids the use of hardcoded credentials or connection strings, leveraging Azure's managed identity and token-based systems.
  • Input Sanitization and Injection Prevention: The reference material explicitly warns against string interpolation in database queries, which is a common vector for injection attacks. It provides specific instructions and code examples for using parameterized queries to ensure data is handled safely.
  • Indirect Prompt Injection Surface: The skill provides a mechanism for an agent to ingest data from an external database and perform operations based on that data.
  • Ingestion points: Data enters the context through database read operations such as read_item and query_items in the SKILL.md and query-patterns.md files.
  • Boundary markers: The skill does not define specific prompt delimiters, as it serves as a library/SDK interface rather than a prompt template.
  • Capability inventory: The skill enables the agent to perform full CRUD (Create, Read, Update, Delete) operations on Azure Cosmos DB documents and containers.
  • Sanitization: The skill strongly advocates for and demonstrates the use of parameterized queries, which is an effective mitigation for database-level injection.
  • Trusted Resource Ownership: The skill and its required Python packages (azure-cosmos and azure-identity) are authored by a trusted vendor and represent official SDK implementations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-cosmos-py