stitch-vue-layui-components

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses a bash script to download HTML code and screenshots from Stitch design URLs, typically hosted on Google Cloud Storage domains. This is required for its primary conversion function.
  • [COMMAND_EXECUTION]: The agent is instructed to execute local bash scripts and standard Node.js development commands, such as npm install and npm run dev, to set up and verify the generated project environment.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it processes external HTML data fetched from remote URLs.
  • Ingestion points: temp/source.html (downloaded design content).
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.
  • Capability inventory: Write (file creation), Bash (script and npm execution).
  • Sanitization: No explicit validation or filtering of the source HTML content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:13 AM
Security Audit — agent-trust-hub — stitch-vue-layui-components