genpage

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill utilizes standard command-line interfaces, including the Power Platform CLI (pac) and Azure CLI (az), to manage environment authentication and resource deployment. These operations are essential for the skill's purpose and are conducted using established vendor tools.
  • Dynamic Code Generation: A primary function of this skill is to generate React-based TypeScript code (.tsx) at runtime based on user specifications. This process is managed through a multi-phase workflow that includes requirement gathering, planning, and a code generation step using specialized subagents.
  • Indirect Prompt Injection Surface: The skill processes user-provided descriptions to influence the final code output. To mitigate potential risks from untrusted input, the skill implements a mandatory planning phase (genpage-planner) and utilizes specific code generation rules to ensure the resulting components adhere to safety and architectural standards.
  • Subagent Orchestration: The skill coordinates several specialized subagents (e.g., entity builders, planners) via the Task tool. This modular approach helps isolate different responsibilities, such as schema creation and UI generation, providing a structured execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:26 AM
Security Audit — agent-trust-hub — genpage