prototype
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [SAFE]: The skill incorporates security best practices for prototyping, such as mandating in-memory state by default, isolating throwaway code from production paths, and ensuring prototypes are clearly identified as non-production code.\n- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate executable logic modules within HTML script tags and React components for UI variations. While this is the primary purpose of the skill, it involves assembling executable code from user-influenced templates.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies user-provided prompts and surrounding project code as the primary sources for determining prototype logic and structure.\n
- Ingestion points: User prompts and local project context are used to define the prototype's requirements (SKILL.md).\n
- Boundary markers: The instructions do not specify the use of delimiters or instructions to the LLM to ignore potentially malicious embedded content within the user input.\n
- Capability inventory: The skill facilitates the creation of HTML and TSX files and references project task runners like pnpm (SKILL.md).\n
- Sanitization: There are no instructions for sanitizing or validating user-provided logic before it is incorporated into the generated prototype artifacts.
Audit Metadata