Skills
Navigate
skills/hanshou101/open-design/agent-browser/Gen Agent Trust Hub

agent-browser

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to verify and install dependencies, specifically running npm i -g agent-browser and agent-browser install to set up the automation environment.
  • [COMMAND_EXECUTION]: It manages browser instances by launching Google Chrome with remote debugging enabled (--remote-debugging-port=9223) and a dedicated user data directory in /tmp.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the agent-browser CLI from the npm registry and fetches dynamic instructional content from remote repositories using the agent-browser skills get command.
  • [SAFE]: The skill includes comprehensive safety rules that prevent the agent from performing sensitive operations like form submission or data deletion without explicit user consent, and it mitigates indirect prompt injection by explicitly marking page content as untrusted.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 06:45 AM