create-agent-tui
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides templates for executing shell commands through a dedicated
shelltool and an optional!shortcut. These features are standard components for the type of 'coding agent' the skill is designed to build. - [EXTERNAL_DOWNLOADS]: The generated project template fetches model metadata from the official OpenRouter API (
openrouter.ai) to support the/modelcommand functionality. - [DATA_EXPOSURE]: The skill generates code with tools for comprehensive file system interaction (read, write, edit, and search), which are essential for its intended use case as a development assistant.
- [PROMPT_INJECTION]: As a template for an AI agent, the generated code inherently possesses an attack surface for indirect prompt injection via the processing of untrusted files or search results. This is a functional characteristic of the intended application rather than a security defect in the skill itself.
Audit Metadata