Skills
skills/circlemind-ai/smooth-sdk/smooth-browser/Gen Agent Trust Hub

smooth-browser

Warn

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill operates by invoking the smooth command-line utility. It executes shell commands to manage browser sessions, profiles, and configurations, including sensitive actions like smooth evaluate-js which runs arbitrary JavaScript in the browser context.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the smooth-py Python package from an external registry (PyPI). It also directs users to the external domain app.smooth.sh for API key management and account upgrades.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. Because it is designed to scrape and interact with arbitrary websites, malicious instructions embedded in those websites could influence the behavior of the AI agent executing the browser tasks.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 09:58 AM