zcode-agent-kit@0.2.39
Local ZCode provider kit: run GLM-5.3 / GLM-5.3-Flash from your own ZCode Desktop account inside your own agent harnesses (OMP, pi, Claude Code, Codex, OpenCode, Cline, Kilo Code, Aider, Continue, Goose).
AI Security Review
scanned 14d ago · by lpm-firewall-aiThe inspected lifecycle hook only displays a setup hint, and the flagged dynamic evaluation and network behavior occur in the proxy’s captcha and local account-management functions. The inspected source supports intended package functionality and does not establish an attack surface.
Decision evidence
public snapshot- The postinstall hook only prints a message asking the user to run setup; it does not run setup automatically.
- The proxy manager verifies that a process belongs to this package before treating it as its own.
- The captcha evaluation runs inside the captcha page and loads its SDK content.
- The flagged account request sends its key to the configured local proxy host.
- Codex setup creates an isolated home; OMP edits a managed configuration block.
Source & flagged code
11 flagged · loading sourcePackage defines install-time lifecycle scripts.
package.jsonView on unpkgInstall-time lifecycle script is not statically allowlisted and needs review.
package.jsonView on unpkgFindings
Affected versions and remediation
This report applies to zcode-agent-kit@0.2.39.
See all versions of zcode-agent-kit for other recorded verdicts.
- Review the evidence and your use of zcode-agent-kit@0.2.39 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.