skills/athevon/genjutsu/design-audit/Gen Agent Trust Hub

design-audit

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends using npx to execute well-known diagnostic tools including pa11y, source-map-explorer, and vite-bundle-visualizer. These packages are sourced from the official npm registry, which is a well-known and trusted service for development tools.
  • [COMMAND_EXECUTION]: The skill provides numerous grep commands designed to perform static analysis on the project's source code. These commands are diagnostic in nature, identifying specific code patterns related to design and accessibility (e.g., checking for hover transitions, accessibility markers, and layout property animations) within the local environment.
  • [PROMPT_INJECTION]: The instructions contain no patterns indicative of prompt injection, such as attempts to override safety filters, disregard previous instructions, or switch the agent into a restricted mode.
  • [DATA_EXFILTRATION]: No patterns for data exfiltration or credential harvesting were identified. The network operations are limited to standard diagnostic tools fetching analysis data for the local user.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:46 PM
Security Audit — agent-trust-hub — design-audit