skills/adobe/skills/testing-blocks/Gen Agent Trust Hub

testing-blocks

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run standard development commands such as npm run lint and npm test to validate code quality and functionality within the project environment.
  • [EXTERNAL_DOWNLOADS]: The instructions include installing industry-standard libraries like vitest, playwright, and jsdom from the npm registry. It also mentions interacting with GitHub via gh pr checks, which are all standard developer activities.
  • [DYNAMIC_EXECUTION]: The skill provides a template for a temporary Playwright test script to be executed locally with node. This is a routine part of functional testing and does not involve untrusted remote code.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves navigating to test content URLs (local or AEM preview) to validate rendered blocks. While this is an ingestion point for external data, it is a standard part of the web development workflow. Ingestion points include test content URLs in SKILL.md; boundary markers are absent; capabilities include subprocess execution (npm/node) and browser control; no specific sanitization is defined for the page content, which is typical for development-time validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:48 AM