prototype
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses potentially untrusted data to determine its core branching behavior.
- Ingestion points: The decision between logic and UI prototyping branches is based on the user prompt and surrounding code context.
- Boundary markers: The skill does not implement boundary markers or instructions to ignore commands that may be embedded within the processed prompt or code.
- Capability inventory: The skill enables the agent to write executable files (HTML, JavaScript, and TSX) and provides commands for the user to execute these files within the local project environment.
- Sanitization: There is no evidence of validation or sanitization routines for the data that influences the agent's logic flow.
Audit Metadata