create-mobile-app
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill employs the
Bashtool to perform essential environment validation and project lifecycle management. This includes verifying the development toolchain (Node.js, npm, Azure CLI) and executing Power Apps CLI commands for project initialization and Dataverse synchronization. - External Resource Integration: It leverages standard, well-known utilities from public registries, such as using
npxto run theqrcodepackage. It also assumes the use of application templates sourced from trusted vendor repositories, ensuring a consistent and secure starting point for development. - Data Ingestion and Processing: As a central orchestrator, the skill processes user-defined application briefs and delegates tasks to specialized sub-agents. This ingestion of external data represents a standard attack surface for indirect prompt injection, which is mitigated by four distinct user approval gates and automated structural validation of the generated application code.
- Secure Credential Handling: The workflow facilitates the configuration of Entra ID authentication but maintains a strong security posture by explicitly instructing that no secrets or tokens be stored in the project's configuration files, relying instead on secure CLI-based authentication flows.
Audit Metadata