Is @microi.net/cli safe?
Microi吾码 AI 开发 CLI 与多宿主 Plugin：服务器连接、Skills、MCP、V8 同步和低代码交付
This server can change things — files, a browser, a database, or paid online services. Limit what it can reach.
Why: writes or deletes files; controls a web browser.
What it can do
- Starts other programs
- Writes or deletes files
- Reads files
- Controls a web browser
- Calls internet services
Tools it offers your AI (3):
- microi_codex
- microi_profiles
- microi_codex_action
How to use it safely
- ✓ It starts another program (often a browser for sign-in, or a bundled binary). Install it only from the official package.
- ✓ Point it at one project folder, never your home directory or a whole drive.
- ✓ Only give it the folders it needs; files it reads can end up in the AI’s context.
- ✓ Use a separate browser profile without your logged-in accounts.
- ✓ Content it fetches from the internet can carry prompt-injection instructions.
- ✓ Pin the version (below) so an update can't change what it does without you noticing.
Code patterns worth reviewing
Automated pattern matches in the published package. Some are expected for this kind of server, and some may be false positives — they are pointers for review, not confirmed vulnerabilities.
Command injection risk
The agent appears to pass input into a shell or command execution path.
scripts/mcp-codex-stdio-adapter.js:11
Unsafe dynamic code execution (eval/Function)
The agent appears to evaluate dynamically constructed code (eval, new Function, or similar).
skills/microi.v8.js:2083
Install it pinned
{
"mcpServers": {
"cli": {
"command": "npx",
"args": ["-y", "@microi.net/cli@6.2.0"]
}
}
}Check your whole MCP setup
Agent Verify checks the servers in your Claude, Cursor and VS Code config — including whole-drive access and keys stored in plain text.
Maintain @microi.net/cli?
Show users you've thought about access: add the badge below. If something here is wrong or you've released a fix, ask for a re-scan — we update pages on request.
[](https://aimodularity.com/agentverify/mcp/microi-net-cli/)
Agent Verify reads the package published on npm as text — it is never installed or run. Ratings describe capability, not intent, and are an automated, evidence-based check, not a guarantee. Scanner 2.0.0.