generate-ui-from-brand
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
dembrandtNode.js package vianpxto perform design crawling and token extraction. This package is retrieved from the public NPM registry and is a resource owned by the skill author. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from arbitrary external URLs or
DESIGN.mdfiles to extract brand tokens and UX rules. This process is susceptible to indirect prompt injection if the source content contains malicious instructions intended to manipulate the agent's output during the UI specification phase. - Ingestion points: External URL crawling and design token extraction tools identified in Step 1.
- Boundary markers: The instructions do not define clear delimiters or "ignore instructions" wrappers for the data extracted from web sources.
- Capability inventory: The skill utilizes CLI execution (
npx dembrandt) and generates functional CSS and layout specifications. - Sanitization: While the skill applies normalization logic (rounding values and mapping to a semantic scale), it does not explicitly sanitize the extracted content for natural language injection patterns.
Audit Metadata