@tiens.nguyen/gu-cli@1.0.802
Gu CLI — the gu terminal plus the local worker that runs agent / OCR / PDF / embedding jobs on your Mac (Ollama / MLX / OpenAI-compatible).
AI Security Review
scanned 14d ago · by lpm-firewall-aiSource inspection found a package-aligned worker API flow and a postinstall PATH helper, but no concrete credential theft, malicious payload execution, or unconsented agent-control modification. The scanner’s execution and network signals correspond to inspected CLI features and do not establish an attack.
Decision evidence
public snapshot- package.json maps the CLI entry points and runs install-path.mjs during postinstall.
- The REPL sends coding keys to its configured worker API; the default API is the package’s own service, and the request uses the worker key for authentication.
- The inspected hooks and MCP configuration code reads project and user configuration paths; it does not show an install-time write to an agent control surface.
- Inspected execution-related modules support package functions: MongoDB setup, worker CLI operation, provider setup, per-request proxying, graceful agent stopping, and local API startup.
- install-path.mjs gates its PATH setup on npm global-install context.
- Static hints flagged credential forwarding, lifecycle behavior, and process execution, but the inspected source did not establish credential theft or unconsented agent-control modification.
Source & flagged code
13 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
Findings
Affected versions and remediation
This report applies to @tiens.nguyen/gu-cli@1.0.802.
See all versions of @tiens.nguyen/gu-cli for other recorded verdicts.
- Review the evidence and your use of @tiens.nguyen/gu-cli@1.0.802 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.