agent-browser

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the agent-browser package from the NPM registry. This tool is maintained by a trusted organization (Vercel Labs), which is identified as a safe source for development tools. \n- [COMMAND_EXECUTION]: Shell commands are used to manage browser sessions, including launching Google Chrome with remote debugging flags and executing browser control actions through the CLI. These commands use isolated temporary directories for user data, preventing exposure of the user's primary browser profile. \n- [PROMPT_INJECTION]: The skill includes explicit defensive instructions to protect against indirect prompt injection by treating all page content as untrusted evidence rather than instructions and requiring action-time confirmation for sensitive operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 07:23 PM