prototype
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided UI descriptions to generate and integrate code into a project. Ingestion points: User descriptions of UI components (e.g., 'a toast', 'the pricing card') are ingested to guide code generation in Phase 1. Boundary markers: No explicit boundary markers or delimiters for user input are defined to prevent potential injection of malicious instructions within UI descriptions. Capability inventory: The skill has file writing capabilities (creating files in '/prototypes/') and the ability to integrate generated code into the main project files in Phase 6. Sanitization: There is no explicit sanitization or validation of the user-provided descriptions mentioned before the agent uses them to generate UI code.
- [DYNAMIC_EXECUTION]: The skill generates executable UI code (HTML, CSS, and JavaScript) dynamically based on user requirements. Evidence: Phase 4 involves building a prototype surface by creating new files or self-contained HTML files with inline CSS and JavaScript logic based on the design exploration results.
Audit Metadata