qa-testing-playwright

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides thorough documentation for web testing best practices, including locator strategy and CI/CD integration. All external references and tools originate from trusted organizations such as Microsoft (Playwright) and well-known services (BrowserStack, Chromatic).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with external web content via Playwright, which inherently creates an attack surface for indirect prompt injection through browser automation.
  • Ingestion points: The agent ingests untrusted data from DOM elements, page content, and attributes while interacting with arbitrary web pages as defined in test scripts.
  • Boundary markers: The skill does not explicitly define boundary markers for untrusted content, though it emphasizes structured testing and semantic locators which provide architectural boundaries.
  • Capability inventory: Playwright provides extensive capabilities including browser navigation, element interaction (clicking, typing), network request interception, and file system writes for traces and screenshots.
  • Sanitization: The skill relies on Playwright's native interaction APIs; no custom sanitization logic for page content is implemented or required for the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 02:03 PM