eve-web-ui-testing-agent-browser

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill instructions facilitate the installation of the agent-browser utility via npm and Homebrew. The underlying repository vercel-labs/agent-browser is a recognized trusted source, which downgrades the severity of the external dependency.
  • COMMAND_EXECUTION (SAFE): The provided shell templates for automation (e.g., authenticated-session.sh and capture-workflow.sh) demonstrate standard usage of the CLI tool without any malicious or hidden commands.
  • REMOTE_CODE_EXECUTION (LOW): The skill supports dynamic JavaScript execution within the browser context via the eval command. This is an expected core feature for browser automation and is documented with security recommendations, such as using environment variables for sensitive data.
  • DATA_EXPOSURE (SAFE): The skill includes explicit security guidelines to prevent the exposure of session tokens and credentials, specifically advising against committing state files to version control and promoting the use of environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:37 PM