go-playwright

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of Playwright drivers and browsers. It provides a command to fetch these components from the official community repository on GitHub.
  • [COMMAND_EXECUTION]: To function, the skill executes shell commands for environment setup and initiates browser processes via the Playwright Go library. These actions are standard for the intended automation purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to automate web browsers, which involves navigating to and processing data from external, untrusted websites. This constitutes an attack surface where malicious content on a webpage could attempt to influence the agent's behavior.
  • Ingestion points: Web page content accessed via navigation and locator methods in Playwright scripts.
  • Boundary markers: No specific delimiters or "ignore" instructions for web content are defined in the provided implementation examples.
  • Capability inventory: The skill can navigate the web, click elements, type text, and save/load session cookies to the local filesystem.
  • Sanitization: No explicit sanitization or filtering of webpage content is implemented in the provided patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 03:15 PM