playwright

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates browser automation and interaction with external web content, which presents a surface for indirect prompt injection if an agent processes instructions found on remote pages.\n
  • Ingestion points: Web navigation and content reading through page.goto(), page.content(), and locators like page.getByText() in SKILL.md.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided in the documentation examples.\n
  • Capability inventory: Full browser control including element interaction (click, fill), file system operations (screenshot, saveAs), and session state management (storageState) in SKILL.md.\n
  • Sanitization: No sanitization of external web content is demonstrated in the provided code snippets.\n- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the Playwright framework and browser binaries from well-known official repositories (npm and Microsoft's registries).\n- [COMMAND_EXECUTION]: The documentation includes standard shell commands for initializing projects and installing environment dependencies (e.g., npm init, npx playwright install).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 01:22 AM