🧰 Cursor CLI

The items that name it 4

• What is an agent harness (and how do you secure one)?
  articleas affected products2026-09-14

  tested in TrustFall; executes project-defined MCP servers on folder trust acceptance

• TrustFall: 1-click coding agent RCE in Claude, Cursor, Copilot
  writeupas tools2026-05-07

  Agentic coding CLI; compared for MCP trust dialog behavior (shows MCP-specific warning but no enumeration)

• Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
  articleas tools

  AI coding agent found affected by a repository-supplied setup command executing before workspace-trust prompt

• Amazon Kiro Prompt Injection Can Exfiltrate Sensitive Data Through Kiro Powers
  articleas affected products

  Zero-click RCE via indirect prompt injection writing malicious executable to workspace and executing it

In every workspace you can read 5