azure-ai-projects-ts
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill content is primarily documentation and boilerplate code for official Microsoft Azure SDKs.
- [CREDENTIALS_UNSAFE] (SAFE): Credential access via getWithCredentials() is a legitimate management feature, accompanied by clear warnings against logging and recommendations for AAD.
- [EXTERNAL_DOWNLOADS] (SAFE): All referenced libraries are trusted official packages hosted on the standard npm registry.
- [PROMPT_INJECTION] (SAFE): The evaluations module provides an interface for custom evaluators. While processing external responses via templates is a standard ingestion point (Ingestion: EvaluationRow; Capability: Tool access via client.agents; Sanitization: None), the skill operates as a development guide for a trusted cloud service and does not include malicious override patterns.
Audit Metadata