entra-app-registration

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • User Input Handling in Generated Commands: The skill creates CLI commands and code snippets based on user-provided data like application names and redirect URIs. While this is essential for its functionality, it represents a surface where maliciously formatted user input could potentially alter the intended command. This is a common consideration for skills that generate executable code or CLI strings.
  • Ingestion points: User-provided variables such as application names and redirect URIs enter the agent context in SKILL.md and references/cli-commands.md.
  • Boundary markers: No specific delimiters or 'ignore embedded instructions' warnings are used when interpolating these variables into command templates.
  • Capability inventory: The skill involves executing Azure CLI commands (az ad app create) and generating source code for Python, .NET, and Node.js.
  • Sanitization: The provided templates do not include explicit validation or escaping logic for external content before it is processed by the command line or interpreted as code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:10 AM