azure-developer-cli

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes local repository files including azure.yaml, infrastructure-as-code files (Bicep/Terraform), and deployment scripts. This represents a standard surface for indirect prompt injection common in development tools, where malicious content in a processed file could attempt to influence agent behavior.
  • Ingestion points: Processes azure.yaml, infra directory content, source code projects, and pipeline definitions.
  • Boundary markers: None explicitly defined for interpolated data.
  • Capability inventory: Executes standard development CLI tools including azd, az bicep, and terraform.
  • Sanitization: Not explicitly implemented; the skill relies on the user's local environment security and standard CLI tool validation.
  • [EXTERNAL_DOWNLOADS]: The skill references official configuration schemas and technical documentation from trusted sources including Microsoft Learn and official Azure/GitHub repositories. These references are essential for maintaining up-to-date development standards and do not involve untrusted remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 06:44 PM
Security Audit — agent-trust-hub — azure-developer-cli