alterlab-vcd-ui-designer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it is designed to ingest and act upon data from external, potentially untrusted sources.
- Ingestion points: The agent is instructed to perform web searches for design guidelines (Material Design, Apple HIG, WCAG) and to read existing project files, including brand guidelines, user research findings, and screenshots.
- Boundary markers: There are no instructions defining specific delimiters or safety prompts to ignore commands embedded within the external research data or project files.
- Capability inventory: The agent has the capability to write multiple types of structured markdown files (
{project}-wireframe-spec.md,{project}-design-system.md,{project}-ui-audit.md) to the local project directory. - Sanitization: The skill lacks logic to sanitize, validate, or filter instructions that might be contained within the design materials or web content it retrieves before generating its own outputs.
Audit Metadata