playwright-testing

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Data Exposure & Exfiltration] (SAFE): The skill demonstrates secure handling of sensitive data by recommending environment variables (process.env.TEST_USER_PASSWORD) rather than hardcoded secrets. It uses a local file (auth.json) for session persistence, which is standard practice in automated testing.
  • [Indirect Prompt Injection] (LOW): As this skill facilitates web automation, it creates a surface where the agent might ingest untrusted content from websites during test execution.
  • Ingestion points: page.goto() and locators like page.getByText().
  • Boundary markers: None specified in the templates.
  • Capability inventory: Shell command execution (npx playwright test), network request interception (page.route), and file system writes (download.saveAs).
  • Sanitization: The skill does not provide specific sanitization logic, as it is a template for testing rather than a data processing pipeline.
  • [Prompt Injection] (SAFE): No instructions designed to override agent safety protocols or bypass system constraints were found.
  • [External Downloads] (SAFE): References to external components (GitHub Actions) use trusted, well-known versions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:03 PM