@linzumi/cli@1.0.113
Linzumi CLI — point a Codex agent at the real code on your laptop, with your team watching and steering from shared threads.
AI Security Review
scanned 3mo ago · by lpm-firewall-aiNot malicious: all observed sensitive behavior is activated by explicit CLI commands and is package-aligned. Warn because it can mutate an AI-agent configuration/control surface and provide MCP capabilities.
Decision evidence
public snapshot- dist/index.js: wx() writes ~/.codex/config.toml during user-invoked runner setup.
- dist/index.js: connect launches Codex with a Linzumi MCP server and scoped token.
- dist/mcp-server.mjs exposes MCP tools that can read project/thread context and post messages.
- dist/index.js: bundled reconnect summarizer may use configured Groq/OpenRouter API keys.
- package.json has no preinstall/install/postinstall lifecycle hooks.
- bin/linzumi.js only imports and invokes dist/index.js after explicit CLI execution.
- scripts/compute-node-reset-e2e.mjs is a manual localhost E2E test using temporary state.
- mcp config prints configuration to stdout; it does not itself modify Codex/Claude settings.
Source & flagged code
8 flaggedPackage source references child process execution.
dist/cloud-supervisor.mjsView on unpkg · L8A single source file combines environment access, network access, and code or shell execution; review context before blocking.
dist/cloud-supervisor.mjsView on unpkg · L2Findings
Affected versions and remediation
This report applies to @linzumi/cli@1.0.113.
See all versions of @linzumi/cli for other recorded verdicts.
- Review the evidence and your use of @linzumi/cli@1.0.113 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.