zcode-agent-kit@0.2.21
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 install hook is limited to a setup hint, while explicit CLI setup can install an extension that runs within OMP's request lifecycle. This warrants a warning for guarded agent extension setup, but the inspected behavior does not establish a concrete malicious attack.
Decision evidence
public snapshot- The postinstall hook only prints a setup hint; it does not invoke setup.
- The OMP adapter writes a package-owned autostart extension into the user's OMP extensions directory during setup.
- The extension runs on OMP provider requests and starts a local health check using the kit key.
- The CLI exposes setup and integration as explicit commands.
- The inspected install hook does not automatically mutate agent configuration.
- The extension's health request targets a loopback address, and its start behavior is gated on the selected provider being zcode.
Source & flagged code
7 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 unpkgPackage source references a known benign dynamic code generation pattern.
zcode-proxy-src/src/proxy/captcha-happy.tsView on unpkg · L667Findings
Affected versions and remediation
This report applies to zcode-agent-kit@0.2.21.
See all versions of zcode-agent-kit for other recorded verdicts.
- Review the evidence and your use of zcode-agent-kit@0.2.21 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.