playwright-testing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents tools and code patterns that ingest untrusted data from external websites. \n
  • Ingestion points: The tools described, such as run_playwright_a11y_tree, and the AxeBuilder patterns ingest DOM structure and accessibility tree content from arbitrary web pages into the agent's context. \n
  • Boundary markers: No specific delimiters or instructions to ignore embedded instructions are included in the provided code templates. \n
  • Capability inventory: The skill utilizes browser interaction capabilities, including the execution of arbitrary JavaScript within the page context via page.evaluate. \n
  • Sanitization: There are no patterns shown for sanitizing or filtering external content before it is processed by the agent. \n- [SAFE]: The skill references and downloads dependencies from well-known and trusted sources. \n
  • External resources: It utilizes official GitHub Actions (e.g., actions/checkout, actions/setup-node) and standard packages from the NPM registry (playwright, @axe-core/playwright). \n
  • CI Integration: The provided GitHub Actions workflow follows standard practices for testing environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:43 AM
Security Audit — agent-trust-hub — playwright-testing