skills/dawitlabs/ui-skills/uiux/Gen Agent Trust Hub

uiux

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the Playwright testing framework (@playwright/test) and browser binaries using npx. These are well-known, official tools provided by Microsoft.
  • [COMMAND_EXECUTION]: The skill generates and executes local Node.js scripts (_uiux_screenshot.mjs, _uiux_auth.mjs) for browser automation and screenshot capture. It also interacts with the local development server using curl and project-specific start commands.
  • [CREDENTIALS_UNSAFE]: The skill prompts users to provide test credentials via environment variables for authenticating browser sessions. It stores resulting session state locally in /tmp/uiux-auth-state.json for visual auditing of protected routes.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection via project configuration files. * Ingestion points: Reads DESIGN-BRIEF.md from the project root and iterates through application route files. * Boundary markers: None are defined to isolate external file content from agent instructions. * Capability inventory: The agent can modify project source code, execute shell commands, and perform local network requests to the dev server. * Sanitization: No validation or filtering is performed on the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 09:47 AM