gs-prototype

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions and documentation describe running shell commands for installation and operation. README.md suggests using npx to install the skill from the vendor's repository. SKILL.md instructs the agent to execute project task runners such as pnpm, python, or bun to launch UI prototypes.
  • [DYNAMIC_EXECUTION]: The primary function of the skill is to dynamically generate and execute code artifacts. It creates standalone HTML files for logic demos (LOGIC.md) and React/framework-specific components for UI variations (UI.md). This behavior is intended and central to the skill's purpose of rapid prototyping.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it generates executable code based on potentially untrusted data.
  • Ingestion points: User prompts and existing project code are used to determine the structure and content of the generated prototypes (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from obeying commands embedded within the user's project or prompts.
  • Capability inventory: The skill has the capability to write files (HTML, TSX) and execute shell commands (pnpm, python, bun, npx).
  • Sanitization: There is no explicit sanitization or validation of the user-provided descriptions before they are used to generate the prototype's logic or UI structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 09:35 AM