azure-vm

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill refers to the installation of the 'semantic-kernel' Python package and the 'Microsoft.SemanticKernel.Agents' package. These are official, well-known libraries from Microsoft, which is a recognized trusted vendor.
  • [PROMPT_INJECTION]: The skill's primary function involves processing user-provided Azure architecture requirements, which creates a surface for indirect prompt injection. Evidence: 1. Ingestion: Azure architecture selection and cost modeling inputs. 2. Boundaries: No explicit delimiters or isolation instructions are provided to separate user data from agent instructions. 3. Capabilities: Operational tasks are delegated to the Microsoft Agent Framework tool ecosystem. 4. Sanitization: The skill does not specify any sanitization or validation logic for external inputs.
  • [SAFE]: No malicious logic, obfuscation, unauthorized system access, or persistence mechanisms were detected. The skill is designed as an instructional wrapper for official cloud management frameworks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 05:44 PM