skills/microsoft/learn-microsoft-agent-framework-with-foundry-zavashop-supply-chain-workshop/agent-framework-workflows-csharp/Gen Agent Trust Hub
agent-framework-workflows-csharp
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [Secure Credential Handling]: The skill correctly encourages the use of
DefaultAzureCredentialandAzureCliCredentialfor authentication. It explicitly advises against using hardcoded API keys or connection strings, which is a critical practice for preventing accidental credential exposure. - [Trusted Software Dependencies]: The skill uses official Microsoft NuGet packages for agent and workflow functionality. These are hosted on a well-known, trusted package registry, reducing the risk of supply chain attacks.
- [Data Ingestion Considerations]: The framework facilitates building workflows that ingest and process user-provided input across multiple agents. While standard for its purpose, developers using this SDK should implement sanitization and boundary markers to manage untrusted data, a consideration associated with indirect prompt injection surfaces.
- [Resilient Process Management]: Features such as
CheckpointManagerand Human-in-the-Loop (HITL) ports are documented for managing long-running workflows. These patterns provide structured state persistence and manual verification steps, which can enhance the operational security and reliability of complex agent systems.
Audit Metadata