agent-browser

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The tool includes an eval command that allows execution of arbitrary JavaScript within the browser context. This capability is standard for advanced browser automation but should be used cautiously as it can interact with the DOM and session data.
  • [DATA_EXFILTRATION]: The skill can access sensitive browser data such as cookies and localStorage, and provides commands to save this state to local files (state save). While documented as a feature for session persistence, users must ensure these state files are managed securely and not exposed.
  • [PROMPT_INJECTION]: As the skill is designed to navigate and extract data from arbitrary websites, it is inherently susceptible to indirect prompt injection. Malicious content on a web page could potentially contain instructions intended to influence the agent's behavior during the scraping or interaction process.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 02:14 PM