NYC
skills/smithery/ai/browser-use/Gen Agent Trust Hub

browser-use

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • Remote Code Execution (CRITICAL): The automated scan identified five instances of the command curl -fsSL https://browser-use.com/cli/install.sh | bash. This is a classic 'curl-pipe-bash' vulnerability.
  • Evidence: Detected via automated security scan alerts.
  • Risk: This allows the server at browser-use.com to execute arbitrary commands on the agent's host system. The script is fetched and executed in a single step, bypassing any manual review or local security controls.
  • Trust Status: browser-use.com is not on the list of Trusted External Sources. Per policy, piped remote execution from untrusted sources is a CRITICAL finding.
  • External Downloads (HIGH): The skill downloads and executes remote executable content (shell scripts) during operation, which creates a significant attack surface for supply chain attacks.
Recommendations
  • CRITICAL: Downloads and executes remote code from untrusted source(s): https://browser-use.com/cli/install.sh - DO NOT USE
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 07:27 AM