@linzumi/cli@1.0.233
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-aiStatic hints overstate bundled dependency primitives: the observed new Function is schema compilation, and the tunnel artifact contains bundled networking code. The reviewed package has no lifecycle hooks and its sensitive capabilities are activated through explicit CLI use.
Decision evidence
public snapshot- User-invoked CLI starts a local agent runner that communicates with Linzumi services.
- Bundled schema-validation code uses new Function; no remote payload is fetched or executed by that code.
- package.json has no preinstall, install, or postinstall hook.
- The bin only imports the packaged main module after the user runs linzumi.
- README documents local runner/authentication behavior and trusted-folder operation.
- No credential exfiltration, covert persistence, destructive action, or unconsented foreign AI-agent control-surface mutation was confirmed.
Source & flagged code
17 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@1.0.233.
See all versions of @linzumi/cli for other recorded verdicts.
- Review the evidence and your use of @linzumi/cli@1.0.233 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.