frontend-unit-testing

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on legitimate software testing tasks and follows industry best practices for behavior-driven development and accessibility-first querying.\n- [COMMAND_EXECUTION]: The skill uses pnpm test:run to verify tests, which is a standard development command and appropriate for the context.\n- [PROMPT_INJECTION]: The skill requires the agent to ingest and analyze project source code (Svelte and Python files), which establishes a surface for indirect prompt injection from those files.\n
  • Ingestion points: Component source code (Index.svelte), Python definitions (gradio/components/), and demo files (demo/).\n
  • Boundary markers: None specified; the agent is instructed to read the code directly to understand its behavior.\n
  • Capability inventory: File system access (reading code, writing tests) and shell execution (pnpm test:run).\n
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:18 AM