design-component

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several local utility scripts to automate component scaffolding and verification, including python3 scripts/scaffold_component.py and various Node.js scripts for accessibility and contrast auditing (e.g., axe_audit.mjs, verify_states.mjs).
  • [DYNAMIC_EXECUTION]: The skill provides a Playwright Javascript snippet for the agent to launch a Chromium browser instance, navigate to local component harnesses, and capture screenshots for visual inspection. The results are stored locally at /tmp/x.png.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific documentation and design tokens which serves as an entry point for untrusted data if the project files are compromised.
  • Ingestion points: Reads CLAUDE.md, accessibility/aria-patterns.md, taste/design-taste.md, and tokens/*.json.
  • Boundary markers: None provided in the skill instructions.
  • Capability inventory: Includes shell command execution (Python/Node) and browser automation (Playwright/Chromium).
  • Sanitization: No explicit sanitization is performed on the ingested file content before it is used to generate component specifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 05:32 PM
Security Audit — agent-trust-hub — design-component