agent-browser

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a legitimate browser automation framework produced by the author, featuring proactive security measures such as content boundaries (nonces) and domain allowlisting to protect the agent from malicious web content.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the agent-browser and appium CLI tools via official package managers (NPM, Cargo, or Homebrew) and the download of a Chromium binary. These are verified dependencies necessary for the tool's core functionality.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands to manage browser sessions and perform complex web interactions. It includes guidance on using these commands safely, such as avoiding shell history exposure for credentials.
  • [DATA_EXFILTRATION]: Contains features to extract text content, screenshots, cookies, and clipboard data from web pages. These extraction capabilities are standard for automation and testing tools and are intended for the skill's primary use case of data processing and web interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 01:14 AM