zcode-agent-kit@0.2.40
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-aiSource inspection found that postinstall only prints a setup hint, while harness configuration is performed through the CLI setup flow. The inspected credential request targets the configured local proxy, and the flagged eval occurs in the captcha solver; these facts do not establish a concrete attack.
Decision evidence
public snapshot- package.json postinstall only prints a setup hint; configuration is selected by a later user command.
- setup.mjs delegates setup to the CLI only outside the postinstall-hint branch.
- The inspected proxy authentication request uses its configured local proxy base.
- The Codex adapter writes configuration under a generated isolated home.
- The OMP adapter uses a managed configuration block with takeover rules.
- Captcha eval is part of the guest captcha solver; inspected evidence does not establish an external payload or unrelated execution.
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@0.2.40.
See all versions of zcode-agent-kit for other recorded verdicts.
- Review the evidence and your use of zcode-agent-kit@0.2.40 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.