variant
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied UI descriptions and project styling tokens to generate code variants. This creates a surface where instructions embedded in the design brief or project metadata could influence the generated output.
- Ingestion points: User design briefs (Step 1) and project styling systems/tokens (Step 2).
- Boundary markers: Instructions do not specify delimiters or provide warnings for the agent to ignore instructions embedded in the input data.
- Capability inventory: The skill generates functional UI code (HTML/CSS/JS).
- Sanitization: The skill lacks explicit sanitization or validation logic for external inputs.
- [DYNAMIC_EXECUTION]: The skill generates and writes executable UI code, including a variant picker component with interactive logic.
- Context: The agent builds HTML/CSS components and a management harness that uses logic for URL manipulation and keyboard interaction.
- Source: Code is generated based on a combination of templates provided in the skill documentation and variable user input.
Audit Metadata