@linzumi/cli@1.0.245
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 2mo ago · by lpm-firewall-aiThis is a dangerous, user-invoked agent-control capability rather than confirmed malicious install-time behavior. The lack of lifecycle hooks and self-dependency prevents a publish-block conclusion.
Decision evidence
public snapshot- The CLI exposes an explicit MCP configuration command.
- Its launcher imports and runs the main program with user-supplied command-line arguments.
- The built runner includes remote agent, local command execution, networking, and configuration-management capabilities.
- package.json has no preinstall, install, or postinstall hook.
- The launcher runs only after the user invokes the linzumi command.
- No runtime dependency on @linzumi/cli itself is declared.
Source & flagged code
18 flaggedPackage source references child process execution.
scripts/vendor-codex-app-server-protocol.tsView on unpkg · L13A single source file combines environment access, network access, and code or shell execution with blocking evidence.
Findings
Affected versions and remediation
This report applies to @linzumi/cli@1.0.245.
See all versions of @linzumi/cli for other recorded verdicts.
- Review the evidence and your use of @linzumi/cli@1.0.245 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.