product-ui-prototyping
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a legitimate and transparent workflow for UI prototyping. It utilizes platform tools for image generation and organizes all artifacts within a self-contained local directory (
ui-prototypes/). It includes explicit safety instructions, such as prohibiting the output of secrets or sensitive payloads through the audio notification system. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined content from
experience-story.mdto define screens, actions, and transitions. This ingestion point constitutes a surface for indirect prompt injection, as malicious instructions in the story file could influence the generated UI assets. However, this is the intended primary purpose of the skill and the risk is contained within the design workflow. - Ingestion points: Loads data from
ui-prototypes/<prototype-name>/experience-story.mdto drive the prototyping logic. - Boundary markers: Absent (input is directly used to inform subsequent prompt generation steps).
- Capability inventory: Involves image generation/editing tools and filesystem management (write/delete) within a specific project folder.
- Sanitization: None; the skill relies on the LLM's interpretation of the story to create descriptive UI prompts.
Audit Metadata