grix-connector@4.15.0
Connect local AI coding agents (Claude, Codex, Gemini, Qwen, DeepSeek, Cursor, OpenCode, Pi, OpenHuman, Reasonix) to the Grix scheduling platform. Also serves as an OpenClaw plugin for Grix channel transport.
AI Security Review
scanned 6d ago · by lpm-firewall-aiSource confirms agent trust and permission safeguards can be changed automatically during user-started sessions. This warrants a warning for the residual capability; the inspected postinstall behavior installs the package’s own upgrade helper.
Decision evidence
public snapshot- The postinstall script copies this package’s upgrade guardian into the user’s Grix bin directory.
- Starting a Claude session marks its workspace trusted and suppresses the user’s dangerous-mode permission prompt.
- Codex startup calls an auto-trust helper that writes the project’s trusted level to Codex configuration.
- Cursor launch defaults to trust and full-auto flags unless configured otherwise.
Source & flagged code
25 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references child process execution.
openclaw-plugin/index.jsView on unpkg · L2450Findings
Affected versions and remediation
This report applies to grix-connector@4.15.0.
See all versions of grix-connector for other recorded verdicts.
- Review the evidence and your use of grix-connector@4.15.0 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.