front-end-test

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/with_server.py uses subprocess.Popen with shell=True to execute commands provided via the --server argument. This is the intended functionality for starting and managing application development servers (e.g., npm run dev) during the test lifecycle.
  • [DYNAMIC_EXECUTION]: Several scripts, including scripts/a11y_check.py, scripts/discover_app.py, and scripts/test_module.py, use Playwright's page.evaluate() method to execute JavaScript within the browser context. This is a standard practice for inspecting the Document Object Model (DOM) to perform accessibility audits and site discovery.
  • [INDIRECT_PROMPT_INJECTION]: The skill's discovery phase (scripts/discover_app.py) involves crawling web applications and ingesting their structure (links, forms, headings) into the agent's context. While this creates an attack surface where a target website could attempt to influence the agent via content, the skill uses standard isolation, and the data is primarily used for diagnostic reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 12:55 PM