prototype
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidance for generating prototypes. It includes safety-conscious practices such as keeping prototypes out of production codebases and avoiding persistence by default. It also instructs the agent to gate UI switcher components so they do not appear in production builds.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user prompts to drive code generation for HTML, Javascript, and React components. This is a standard attack surface for development-oriented agents. The skill mitigates this by instructing that prototypes be kept separate from the main codebase and treated as temporary artifacts.
- [COMMAND_EXECUTION]: The instructions mention using project task runners such as pnpm, python, or bun to execute the generated prototypes. This is consistent with the primary purpose of a developer tool and does not involve unauthorized or hidden command execution.
Audit Metadata