cursor-agent-development

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill consists of instructional Markdown files and configuration examples. No executable scripts or malicious instructions were found within the skill content.
  • [COMMAND_EXECUTION]: The documentation provides examples for using the agent CLI to perform development tasks. It highlights security-sensitive flags like --force and --sandbox disabled, advising users on their proper and safe application.
  • [REMOTE_CODE_EXECUTION]: The skill documents a 'Hooks' system that uses JavaScript files located in .cursor/hooks/. The provided examples, such as auto-formatting or committing code, are standard developer workflows and are documented for educational purposes.
  • [CREDENTIALS_UNSAFE]: The guide discusses API key management and environmental configuration. It promotes security best practices, such as using environment variables and .env files while ensuring they are excluded from version control via .gitignore.
  • [EXTERNAL_DOWNLOADS]: The documentation describes integrating with external Model Context Protocol (MCP) servers. The references provided involve standard MCP tool distributions and well-known services.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 06:17 PM
Security Audit — agent-trust-hub — cursor-agent-development