skills/poteto/plugins/cursor-sdk/Gen Agent Trust Hub

cursor-sdk

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and code examples for using the @cursor/sdk package, which is the official SDK for the service. All patterns follow industry best practices for security and resource management.
  • [SAFE]: Network operations described (e.g., interacting with https://cursor.com, https://mcp.linear.app, and https://github.com) are consistent with the skill's stated purpose of building integrations and automation for the Cursor platform.
  • [SAFE]: The skill correctly instructs users to manage sensitive credentials (like CURSOR_API_KEY) using environment variables or secret managers rather than hardcoding them, which is a defensive security posture.
  • [SAFE]: Package installations mentioned (@cursor/sdk, @modelcontextprotocol/server-*) are official, well-known libraries related to the vendor's ecosystem.
  • [SAFE]: Guidance on handling local vs. cloud runtimes includes appropriate warnings about process isolation and permission scoping (e.g., local agents running with caller permissions).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 03:44 PM
Security Audit — agent-trust-hub — cursor-sdk