{
  "id": 17629649,
  "title": "Cloned a Stranger's Repo? Check 6 Agent Config Files Before Claude Code or Codex Opens It",
  "url": "https://urgent.news/2026/11/01/cloned-a-strangers-repo-check-6-agent-config-files-before-claude-code",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-01T16:01:24.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/gabrielanhaia/cloned-a-strangers-repo-check-6-agent-config-files-before-claude-code-or-codex-opens-it-56gb"
  },
  "original_language": "en",
  "account": "Before engaging with a cloned repository containing AI coding tools like Claude Code, Codex, or Gemini CLI, it is crucial to examine six specific configuration files. These files can initiate various operations and potentially pose security risks.\n\nThe first file, .claude/settings.json, contains hooks that run shell commands, an environment block, and helper commands such as apiKeyHelper. Some of these settings are stored in a local version, .claude/settings.local.json, which also gets tracked in Git.\n\nNext is .mcp.json, responsible for project MCP servers. An MCP server with trust set to true bypasses all tool call confirmations, bypassing safety measures.\n\nFor Gemini CLI, .gemini/settings.json handles hooks that execute arbitrary code with user privileges and lists MCP servers. Enabling trust for this folder allows servers to bypass all tool call confirmations, while also potentially bypassing all other validations.\n\nIn Codex, .codex/config.toml and .codex/hooks.json outline project configurations and hooks that could execute arbitrary code with user privileges.\n\nLastly, AGENTS.md, a project-specific configuration file, reads settings either at the project root or from the directory where it is started. It can also include other files using @path imports, which the agent may execute.\n\nBefore trusting a repository, one must inspect these files. This process involves checking the content of the files, verifying that no malicious commands or settings are present, and ensuring they do not bypass safety checks. This precautionary step is vital for maintaining the security and integrity of your development environment.",
  "summary": "Book: Prompt Engineering Pocket Guide Also by me: Thinking in Go (2-book series) — Complete Guide to Go Programming + Hexagonal Architecture in Go My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools Me: xgabriel.com | GitHub You clone a repo to reproduce a bug someone reported. Before you have read a line of its code, you type claude in the…",
  "key_points": [
    ".claude/settings.json contains shell command hooks and environment block",
    ".mcp.json bypasses tool call confirmations when trust is set to true",
    "AGENTS.md can execute other files using @path imports"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}